New: 97,000+ skills indexed from GitHub repos with 100+ stars · every skill safety-checkedBrowse top skillsTop skills
Esc to closeBrowse all skills
Submit a skillBrowse skills
Submit a skillBrowse skills

Agent skill

Fpf Problem Solving

by CodeAlive-AI in CodeAlive-AI/ai-driven-development

Use First Principles Framework (FPF) to decompose problems, architect systems, evaluate alternatives, define quality, recover and replace methods, initiate inquiry from ordinary work, disambiguate…

MITAuto-check passedAgent Workflows

Install Fpf Problem Solving

skills CLI
$ npx skills add CodeAlive-AI/ai-driven-development --skill fpf-problem-solving -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install CodeAlive-AI/ai-driven-development fpf-problem-solving --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/CodeAlive-AI/ai-driven-development.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/fpf-problem-solving .claude/skills/fpf-problem-solving && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
fpf-problem-solving
GitHub stars
155
Token cost
~6.6k tokens
SKILL.md length
3,077 words
Files
420 (incl. scripts)
Skills in repo
22
Repo updated
First seen
Licence
MIT

At a glance

Use First Principles Framework (FPF) to decompose problems, architect systems, evaluate alternatives, define quality, recover and replace methods, initiate inquiry from ordinary work, disambiguate…

  • Works in 4 steps: Match the thinking need to a starting… → Read the _index.md, then the sub-section → Apply in plain language → …
  • Tasks that involve Domain-driven design
  • SKILL.md covers Attribution and license, Use cases, How to navigate and Starter prompt (example —…, plus 1 more section
  • Runs Python scripts from its folder

What it does

Fpf Problem Solving is an agent skill from CodeAlive-AI/ai-driven-development. Use First Principles Framework (FPF) to decompose problems, architect systems, evaluate alternatives, define quality, recover and replace methods, initiate inquiry from ordinary work, disambiguate agent-relative instructions, steer or resume work, surface applicable methods, coordinate development states, bridge domain terms, screen mandatory steps, compare configurations, probe capability, decide under uncertainty, establish causality, reason about time, synthesize ontologies, govern ontic admission, publish…

Its SKILL.md is about 6.6k tokens, which your agent loads only when the skill is triggered. The skill folder holds 424 other files, including scripts (for example `FPF-SKILL-UPDATE-GUIDE.md`, `README-RU.md` and `README.md`).

It sits in Agent Workflows, covering Domain-driven design, Planning and Session handoff. The repository describes itself as: Practices, protocols, and skills for AI-driven software development. Skills and safety hooks for Claude Code, Codex, OpenCode, Cursor, Antigravity, and any agent supporting the… The licence is MIT.

When your agent uses it

  • Tasks that involve Domain-driven design
  • Tasks that involve Planning
  • Tasks that involve Session handoff

Example prompts

  • “/fpf-problem-solving”

Requirements

  • Python 3

Workflow steps

4 steps, taken from the step headings in SKILL.md.

  1. Match the thinking need to a starting point
  2. Read the _index.md, then the sub-section
  3. Apply in plain language
  4. Compose findings across sections

What it can do on your machine

Read from SKILL.md and the folder at commit 25b7b1d. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    Ships 1 file in scripts/ (Python, from the files we listed), which the agent can run.

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    Links to these hosts (documentation or services it may open):

    • github.com
    • creativecommons.org

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Fpf Problem Solving loads about 6.6k tokens when it runs. Until then it costs about 234 tokens; SKILL.md has 3,077 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~234
When it runs · the whole SKILL.md, loaded when a task matches
~6.6k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); the scripts in this folder are not scanned.

SKILL.md

The full file from CodeAlive-AI/ai-driven-development at commit 25b7b1d, republished under its MIT licence (© CodeAlive-AI). 3,077 words, ~6,634 tokens.

Download SKILL.mdSave it as .claude/skills/fpf-problem-solving/SKILL.md (or your agent's skills folder). This skill also uses 419 other files; get the full folder from GitHub.
name
fpf-problem-solving
description
Use First Principles Framework (FPF) to decompose problems, architect systems, evaluate alternatives, define quality, recover and replace methods, initiate inquiry from ordinary work, disambiguate agent-relative instructions, steer or resume work, surface applicable methods, coordinate development states, bridge domain terms, screen mandatory steps, compare configurations, probe capability, decide under uncertainty, establish causality, reason about time, synthesize ontologies, govern ontic admission, publish views, revalidate sources, select representations, and appraise advice. Triggers: FPF, bounded contexts, SoTA packs, assurance calculus, decision theory, operational parsimony, causal/temporal reasoning, architecture, modularity, transformation flows, structural adequacy, cultural evolution, lexical discipline, Parts A-I. Not for simple task planning, general philosophy, or Agile unrelated to FPF.

First Principles Framework (FPF)

Attribution and license

This skill adapts First Principles Framework (FPF) by Anatoly Levenchuk, ailev/FPF, upstream commit fc1e39d8cf3f0aa82fc9bbbabcef76ccfe0044fe. The FPF specification text in sections/ is licensed under CC BY 4.0. Changes: the specification was split into section files and given generated navigation indexes; this SKILL.md adds an agent-oriented router and usage instructions. See the upstream licensing scope. Skill packaging and the splitter are MIT licensed. This adaptation is not endorsed by the FPF author.

An "Operating System for Thought" — a transdisciplinary architecture for reasoning, written in human- and machine-readable pseudo-code. FPF turns raw intelligence (human or machine) into organisationally usable reasoning: explicit bounded contexts, auditable artefacts, multi-view descriptions, and disciplined hand-offs between specialised actors.

Use cases

Use FPF whenever you need to think more rigorously than the situation's default.

  • Decompose a messy, cross-domain problem into parts that can be reasoned about independently
  • Make a high-stakes decision with incomplete evidence — and know what evidence is still missing
  • Get a mixed team to reason together without vocabulary collisions or hidden assumptions
  • Audit whether a conclusion is well-founded or just plausible
  • Transform or transfer an insight without losing its subject, precision, or stated limitations
  • Structure a proposal that must survive scrutiny from multiple expert perspectives
  • Generate alternatives systematically instead of anchoring on the first idea
  • Define what "better" means before comparing options
  • Classify what kind of problem you're facing before searching for solutions
  • Plan how an AI agent should select and sequence its tools under budget and trust constraints
  • Make a decision under uncertainty — identify options, weigh evidence, and commit with an auditable rationale
  • Establish whether X causes Y — or just correlates — and determine what intervention would work
  • Publish a stable multi-view artifact without changing the source semantics
  • Assemble or check a public framework publication form while preserving product-specific bodies and references
  • Develop a holder system's capability for a named Work family and verify transfer in representative Work
  • Synthesize source ontologies for one bounded authoring decision without flattening their local meanings
  • Refresh a SoTA pack, benchmark, or evidence trail when evidence decays or telemetry changes
  • Synthesize architecture candidates, compare structural options, or repair modularity/reuse claims
  • Detect an ontic candidate, decide its first-use disposition, and govern whether a new concept or U-kind should be introduced instead of just renamed
  • Identify the exact system that acts or is intended to change, then trace a lost path from outside use to architecture, production, and recursive builders
  • Discover other systems that may bear relevant consequences before a decision closes
  • Explain how constituent actions perform larger work and whether a replacement preserves each receiving use
  • Recover a reusable method cautiously from several performances, logs, or observations without treating the evidence as the method itself
  • Make instructions usable after a change of speaker, recipient, location, time, or other reference condition
  • Choose the next action during ongoing work, resume interrupted work, or make applicable methods visible when current facts, authority, and stop conditions matter
  • Turn an ordinary handover, result demonstration, or successful workaround into a bounded question with a useful next move
  • Coordinate whether a system or episteme is being explored, shaped, evaluated, or operated without confusing that state with claim assurance
  • Preserve domain vocabulary while recovering which exact FPF value or relation a local term currently claims
  • Recover the actual performer/support configuration for Work and test what survives interruption, handoff, delay, or reconfiguration
  • Decide whether a proposed mandatory step, check, record, wait, or tool use changes a substantive result or only adds ceremony
  • Compare what a finite addition, replacement, or intervention contributes relative to the current configuration
  • Clarify what a claim about human, machine, organizational, or cultural “learning” actually says changed
  • Clarify what “development” or “evolution” means by naming the changed subject, continuity rule, posture, and value basis
  • Probe whether apparent capability loss is really an envelope, support, access, adaptation, enactment, or capability-change issue before choosing redevelopment
  • Revalidate affected decisions when a relied-on source changes and the full set of receivers is unknown
  • Request or reuse a bounded specialist result while preserving supplier authority and the receiving decision
  • Select and combine diagrams, models, records, or other representations for one exact use
  • Compare what structure a reader can correctly recover from an explanation under stated preparation, access, and time constraints
  • Turn build, buy, reuse, outsource, or AI labels into comparable complete ways to obtain one result
  • Check whether advice or an evidence demand helps the recipient’s decision and leads to a feasible next step
  • Apply one selected FPF pattern to a current question and stop at the first useful result
  • Construct a first model, apply an unfamiliar theory, recover an argument, or revise reasoning after a premise changes
  • Connect physical, mathematical, and computational contributions into an interpretable answer
  • Design a measurement relation and determine what its indications can actually resolve
  • Track object identity across observations, describe constrained configurations, and retain information needed to predict change
  • Develop new questions, reusable operations, and branching search from available results
  • Develop a line of thought from working notes, preserving its grounds and the relations that make a later continuation useful

How to navigate

The use cases above help decide WHETHER to invoke FPF. The router below decides WHERE to go once invoked.

Step 1 — Match the thinking need to a starting point
What you need to doStart here
Decompose and model a whole, track continuing objects, constrain configurations, or predict state changes05 Part A → A.1 Holons, A.1.1 Bounded Contexts, A.14 Mereology; A.1.RI object reidentification; A.3.3.CC constrained configurations, A.3.3.TR state change, A.3.3.PI prediction information
Identify, trace, and discover the acting or changed system, find omitted Systems that may bear consequences, then locate the first unsupported dependency from outside use through recursive builders05 Part A → A.1.SCR System Recognition, A.1.CSD Consequence-Bearer Discovery, A.1.STM System-Thinking Long Mantra; 03 FPF Readme → Recover a Lost Path
Assign system roles and responsibilities, recover what “role” means, check permission, or distinguish production work from the identity and completion of its product05 Part A → A.2 System Role Kinds and Assignments, A.2.8.PER Permission; 11 Part E → E.10.ROLE Role Meaning Recovery; 07 A.V → A.15 Role-Method-Work Alignment, A.15.PROD Production Work
Recover a reusable method from several performances or direct evidence without overclaiming Method identity05 Part A → A.3.1.MR Candidate-Method Recovery from Work Evidence
Recover what project, process, or case language directly refers to before modeling it07 A.V → A.15.6 Project, Process, and Case Recovery
Steer, resume, and recovery-test Work by choosing the next action from current facts, resuming after interruption, making applicable methods noticeable, or recovering the actual performer/support configuration and probing interruption, handoff, delay, or reconfiguration07 A.V → A.15.7 Situation-Responsive Work Steering, A.15.8 Work-Performance Configuration and Recovery Testing, A.15.10 Resume Interrupted Work, A.15.11 Make Applicable Methods Noticeable
Screen mandatory work for operational relevance before requiring a step, check, record, wait, cue, or tool use07 A.V → A.11.OP Decision-Relevant Least Action and Operational Parsimony
Request or reuse specialist results for one receiving decision while preserving the other practice’s authority07 A.V → A.15.9 Bounded Result from Another Practice
Select and combine representations for one exact action or decision without treating them as interchangeable09 Part C → C.37 Use-Bounded Representation Selection and Co-Use
Set boundaries on what statements mean, recover agent-relative references after a transfer, distinguish relations from their individuated occurrences, or derive a missing relation claim06 Signature Stack → A.6.B boundary norms, A.6.P.RI agent-relative reference recovery, A.6.REL relation obtaining and occurrences, A.6.RCD relation-claim derivation, declarations, gates, duties, and evidence
Prevent category errors or reconcile ontology premises before extending the framework07 Constitutional Principles → A.7 Strict Distinction, A.7.1 Consequence-Guided Ontological Problem Solving, A.7.2 Premise Reconciliation, A.7.CP Constructive Premise Compact
Evaluate confidence in a claim or artifact — including formality, scope, and reliability of the underlying knowledge08 Part B → B.3 Trust & Assurance; 09 Part C → C.2 KD-CAL / F-G-R scoring, C.2.2 Reliability, C.2.3 Formality
Compose parts into wholes, recover how actions enact larger work, and check constituent-method replacements08 Part B → B.1 Gamma algebra, B.1.5.EW encompassing Work, B.1.5.RS constituent replacement; 09 Part C → C.13 Compose-CAL, C.20 Discipline-CAL
Reason through or coordinate development — initiate inquiry from ordinary work, develop a line of thought through working notes, construct a model, use or compare theories, recover arguments or constructions, revise premises, bridge domain vocabulary, name whether a subject is explored/shaped/evidenced/operated, or develop a new question08 Part B → B.5 Reasoning Cycle, B.5.PI inquiry from ongoing work, B.5.WN working notes, B.5.1 Explore → Shape → Evidence → Operate, B.5.2 Abductive Loop, B.5.3 Domain-Concept Bridge, B.5.4 concept recognition; B.5.FM first model, B.5.RA argument recovery, B.5.RC construction recovery, B.5.RR reasoning revision, B.5.TU theory use, B.5.TC theory comparison, B.5.QD new questions
Enter and apply FPF: choose a starting point or practical entry, find results across a DPF suite, or apply one pattern to a first useful result03 FPF Readme → Start Here, Practical Entries; 11 Part E → E.11.DSG DPF Suite Reference, E.11.PUA Pattern Use
Generate alternatives / construct comparable ways to obtain one result, explore solution space, and keep apparatus use bounded09 Part C → C.38 Comparable Ways to Obtain One Result, C.39 result construction, C.39.RO reusable operations, C.40 branching search, C.40.CD co-development of problems and solutions; C.17 Creativity-CHR, C.18 Open-Ended Search, C.19 Explore-Exploit, C.19.2 Use-Bounded Apparatus Application
Measure and compare options, construct or repair measurement relations, and assess indication resolution07 A.V → A.17-A.19 Characteristics, CSLC & SelectorMechanism; 09 Part C → C.16 MM-CHR, C.16.MR measurement relation, C.16.IR indication resolution, C.16.RM measurement repair; 13 Part G → G.9 Parity / Benchmark Harness
Resolve conflicts across stakeholders or values10 Part D → Ethics, bias audit, conflict optimization
Unify vocabulary or synthesize source ontologies across teams or domains without flattening source-local claims12 Part F → F.0.2 Semantic Synthesis, concept sets, bridges, UTS, lexical continuity
Transform, document, publish, and reuse epistemes, views, or frameworks while preserving subjects and product-specific bodies06 A.IV.A → A.6.2-A.6.4 episteme morphing/viewing/retargeting (separate exact arrow, bounded-use assertion, and current-case judgment), A.6.3.NAR narrative rendering, A.6.3.RT.OE operative expression; 11 Part E → E.4.CM Connected Methods, E.4.PFIP Publication Integration, E.11.PFP Publication Form Profile, E.17 Multi-View Publication Kit
Sharpen expression — repair vague wording, recover exact method/work relations and model/explanation uses, clarify what “learning,” “development,” “evolution,” “interest,” or “curiosity” means in the current claim, surface ambiguity, or restore precision of epistemic / measurement / architecture terms06 A.IV.A → A.6.P.WMR Exact Relation Recovery, A.6.H Wholeness Unpacking; 11 Part E → E.10 model/explanation use, E.10.LRN, E.10.DEV, E.10.INT interest/curiosity, E.10.ARCH, E.17.EFP; 09 Part C → C.2.P, C.16.P, C.30.P
Decide, appraise advice, or compare contributions under uncertainty — compare a finite configuration change to the current configuration, structure options, weigh evidence, and commit with auditable rationale09 Part C → C.11.CRC Configuration-Relative Contribution Comparison, C.11 Decsn-CAL, C.11.DUA Decision-Useful Advice and Evidence Demands
Reason about time and change — distinguish state readings, trends, currentness, and intervention-sensitive change, or recover an actual temporal structure before testing coordination09 Part C → C.27 Temporal Claim Adequacy, C.27.TA Temporal Aspect; 03 FPF Readme → ACTUAL-TEMPORAL-STRUCTURE
Establish causality — climb the causality ladder, construct or challenge a causal model, identify causal structure, and check realizability09 Part C → C.28 CausalUse-CAL, C.28.CM causal-model construction/challenge, C.28.MR mechanism replacement
Connect mathematical and computational reasoning — assess model fit, transfer results, realize computations, repair physical connections, compare symmetry transformations, or construct boundary balances09 Part C → C.29 Mathematical Lens Use, C.29.1 result transfer and symmetry, C.29.2 computational formulation, C.29.3 computational realization, C.29.BB boundary balance; 08 Part B → B.5.MPC physical/mathematical/computational connection, B.5.MPC.R repair
Describe architecture or structural views — characterize structure, unfold constraint-governed structure, produce adequate architectural descriptions and view types, triage cross-scope architectural residuals07 A.V → A.22 STRUCT-CAL, A.22.CGUS; 09 Part C → C.30, C.30.AD, C.30.ASV, C.30.LCA, C.30.ILC, C.30.TFS-REL
Connect transformation flows without collapsing independent structures into one flow or project11 Part E → E.18.NET Network of Transformation-Flow Structures
Synthesize architecture candidates or reconcile several non-isomorphic structures of one practice, then assess modularity/reuse or publish ADR-style projections09 Part C → C.31 Modularity, C.32 Architecture Candidate Synthesis, C.32.MWA Practice Architecture, C.32.PAD, C.32.ADR, C.32.ADA
Assess structural information — compare what a reader can recover from an explanation under stated conditions, or check architecture capture, source return, equivalence, morphisms, or discovery adequacy09 Part C → C.2.8 Extractable Structural Information, C.33, C.34, C.35
Model context-dependent or indeterminate states — represent superposed, probe-coupled, or viability-bounded behaviour09 Part C → C.26 Quantum-Like Modeling Lens, C.26.1 Probe-Coupled Boundary, C.26.2 Enacted Distributed State, C.26.3 Viability-Envelope
Survey a discipline and build, ship, or refresh a reusable toolkit13 Part G → G.1-G.13 SoTA kit, CG-Frame, dispatcher, benchmarks, shipping, telemetry refresh, dashboards, external interop; 09 Part C → C.21 Discipline-CHR
Classify a problem type, test whether a candidate is admissible for a kind judgment, or compare kind identity before claiming a cross-local correspondence09 Part C → C.22 Problem-CHR, C.22.PFR Problematic-For Relation, C.3 Kind-CAL, C.3.2 Kind Judgment, C.3.3 KindBridge
Define quality attributes ("-ilities") as structured bundles09 Part C → C.25 Q-Bundle; 07 A.V → A.17-A.19 Characteristics
Govern ontology — detect an ontic candidate, decide its first-use disposition, and determine whether a new concept or U-kind is warranted11 Part E → E.24 Ontic Introduction Discipline, E.24.CD Ontic Candidate Detection and First-Use Disposition, E.24.UK U-kind Admission and Ontic Settlement
Probe or develop capability — distinguish apparent capability loss from envelope, support, access, adaptation, or enactment failures; when development is separately selected, test whether improvement transfers beyond an exercise11 Part E → E.23.CAE Capability Access and Expression Differential Probe, E.23.CDI Developing Capability for a Named Work Family
Reason about cultural evolution — describe cultural-evolution engineering or repair cultural-evolution wording09 Part C → C.36 Cultural Evolution, C.36.P Precision Restoration, C.36.RP sustaining and renewing shared work
Orchestrate agentic tool use under budgets and trust gates09 Part C → C.24 Agent-Tools-CAL
Trace provenance and revalidate affected uses when a relied-on source changes, or detect refresh debt07 A.V → A.10 Evidence Graph, A.10.1 Revalidate Affected Uses; 13 Part G → G.6 Provenance Ledger, G.11 Telemetry-Driven Refresh & Decay

For complex problems, follow paths across multiple sections — the router shows where to start, not where to stop.

Show full SKILL.md (799 more words)Show less
Step 2 — Read the _index.md, then the sub-section
  1. Open the _index.md of the target section folder — it lists all sub-sections with line counts and descriptions.
  2. Read only the specific sub-section file you need.
  3. Do NOT load entire sections. Pick the narrowest file that serves the user's question.
Step 3 — Apply in plain language

Use plain language for the user. Introduce FPF-internal names (U.Holon, Gamma, F-G-R) only when they add precision the user needs.

Step 4 — Compose findings across sections

When a problem draws from multiple sections:

  1. State each pattern's contribution in one line (e.g., "Bounded Contexts gives us the parts; Trust Calculus scores our confidence in each").
  2. If patterns from different sections appear to conflict, check for category errors via A.7 Strict Distinction — the conflict is usually a level confusion (role vs. function, method vs. work), not a real contradiction.
  3. Synthesize in natural order: decomposition first (what are the parts?), then evaluation (how confident are we?), then resolution (what do we do about gaps?).
  4. Do not just list FPF patterns — weave them into a coherent answer to the user's actual question.

Starter prompt (example — adapt to the user's actual role and need)

You have the FPF specification loaded. Help me structure my project / problem / programme. Use plain language for an engineer-manager. Propose: (1) bounded contexts / specialisations, (2) decision criteria, (3) key alternatives, (4) hand-offs, and (5) missing evidence or tests before commitment. Introduce internal FPF names only when they add precision.

Section INDEX

Structural reference. Each entry is a folder — read its _index.md first, then pick the sub-section. Counts follow upstream H2 headings; the Preface includes its content-free FPF.Preface:End boundary marker.

#SectionSubWhen to use
01Title page0Identify: title, authorship, version date, top-level identity.
02Table of Contents0Navigate: locate a pattern, keyword, query cue, dependency, or neighboring section.
03FPF Readme12Enter, onboard, and recover: choose a starting point or practical entry, understand what each part contributes, connect actions to encompassing work, connect transformation flows, recover a lost path from outside use to recursive builders, or locate licensing and reuse terms.
04Preface22Orient: read philosophy, Architectural Rationale, shared source synthesis, profile choices, whole-combination conditions, uncertainty posture, and purpose/non-goals.
05Part A — Kernel30Decompose, identify, discover, trace, assign, recover, and authorize: holons, bounded contexts, acting/changed-system recognition, consequence-bearing System discovery, outside-use dependency tracing, roles, permissions, candidate-Method recovery from Work evidence, transformers, method/work separation, object reidentification, constrained configurations, state-change rules, predictive information.
06A.IV.A — Signatures29Set boundaries, recover references, derive relations, transform epistemes, and render: recover agent-relative expressions after transfer; distinguish relations from occurrences; recover exact method/work and under-specified service/access relations; derive needed relation claims; keep source, receiving episteme, arrow, use claim, work, and publication distinct; classify statements, construct operative expressions, or render structure faithfully.
07A.V — Principles49Prevent confusion, remove ceremony, recover direct subjects, and steer, resume, or recovery-test Work: category errors, ontology premises, decision-relevant operational parsimony, project/process/case language, situation-responsive next-action choice, interrupted-work resumption, making applicable methods noticeable, performer/support configuration and recovery probes, production-work identity, completion criteria and separate closure authority, measuring, comparing, evidence graphs and changed-source revalidation, bounded specialist results, mechanism suites, transformation-step constraint validity, independent-check gate decisions, constraint-governed unfolding.
08Part B — Reasoning41Compose, evaluate, and coordinate development: structural views (STRUCT-CAL), aggregation (Gamma), constituent actions and encompassing Work, use-preserving Method replacement, trust scores, emergence, inquiry from ordinary work, working-note development, development states, domain-concept bridging, reasoning cycles, first models, concept recognition, theory use/comparison, argument and construction recovery, reasoning revision, new questions, physical/mathematical/computational connections.
09Part C — Extensions96Score, compare, search, and architect: epistemic quality, reader-extractable structural information, typed reasoning, measurement, configuration-relative contribution comparisons, comparable result routes, representation selection and co-use, decision-useful advice and evidence demands, decisions, bounded apparatus use, temporal/causal/math lenses, causal-model construction/challenge, architecture synthesis across non-isomorphic practice structures, structural adequacy, cultural evolution, measurement construction/repair, result transfer, computational formulation/realization, symmetry comparison and boundary balances, reusable operations, branching search, and reproducible construct use.
10Part D — Ethics5Resolve conflicts: ethical trade-offs, bias auditing, safety overrides, conflict optimization.
11Part E — Constitution and Authoring69Enter, apply, clarify, probe, develop, govern, reuse, and publish: practical entry and pattern use, DPF-suite navigation, learning/development/evolution and interest/curiosity claim recovery, connected methods and framework publication forms, capability access/expression probing and development for named Work, edition continuity, multi-view publication, transformation-flow networks, pattern quality, ontic/U-kind governance.
12Part F — Unification22Synthesize and align: bounded semantic synthesis across source ontologies, concept sets, sense cells, bridges with separate bounded-use claims and reliance basis, system-role descriptions, UTS, lexical continuity.
13Part G — SoTA Kit15Harvest and refresh disciplines: SoTA Packs, CG-Frames, dispatchers, provenance ledgers, benchmark harnesses, shipping, telemetry refresh, dashboards, external interop.
14Part H — Reserved0Reserve: preserve the upstream Part H position for future specification content.

© CodeAlive-AI, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 419 other files (scripts) in skills/fpf-problem-solving of CodeAlive-AI/ai-driven-development.

  • SKILL.md
  • FPF-SKILL-UPDATE-GUIDE.md
  • README-RU.md
  • README.md
  • scripts/split_spec.py
  • sections/01-first-principles-framework---core-conceptual-specification/_index.md
  • sections/02-table-of-contents/_index.md
  • sections/03-first-principles-framework-readme/01-start-here.md
  • sections/03-first-principles-framework-readme/02-practical-entries.md
  • sections/03-first-principles-framework-readme/03-decide-whether-fpf-fits.md
  • sections/03-first-principles-framework-readme/04-when-several-transformation-flows-form-one-network.md
  • sections/03-first-principles-framework-readme/05-perform-several-levels-of-work-through-one-action.md
  • sections/03-first-principles-framework-readme/06-recover-a-lost-path-from-outside-use-to-recursive-builders.md
  • sections/03-first-principles-framework-readme/07-one-minute-example.md
  • sections/03-first-principles-framework-readme/08-what-fpf-is.md
  • sections/03-first-principles-framework-readme/09-what-fpf-is-not.md
  • … and 404 more

Open the folder on GitHubat commit 25b7b1d

Compare with similar skills

Fpf Problem Solving next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Fpf Problem Solving compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Fpf Problem Solving this skillCodeAlive-AI/ai-driven-development155—~6.6kAutomated safety check: PassMIT
Planning with FilesOthmanAdi/planning-with-files27k—~2.9kAutomated safety check: PassMIT
Using LWC Memory and Graphssickn33/agentic-awesome-skills47k1 repos~2kAutomated safety check: PassApache-2.0
Planning With FilesOthmanAdi/planning-with-files27k—~3kAutomated safety check: PassMIT
Planning with Files for KiroOthmanAdi/planning-with-files27k—~2.1kAutomated safety check: PassMIT
Ultragoal Multi-Goal LedgerYeachan-Heo/gajae-code2.9k—~8.4kAutomated safety check: PassMIT

Similar skills

  • Planning with Files

    OthmanAdi/planning-with-files

    Keeps a task plan, findings and progress log in markdown files on disk so long agent tasks survive context resets, with Gemini hooks and helper scripts.

    27k GitHub stars~2.9k tokensUpdated yesterday
    Agent WorkflowsAuto-check passed

  • Using LWC Memory and Graphs

    sickn33/agentic-awesome-skills

    Keeps project decisions, research and verified results available across coding-agent sessions through LWC memory, a document Wiki graph and a CodeGraph code index.

    47k GitHub starsUsed in 1 repo~2k tokens
    Agent WorkflowsAuto-check passed

  • Planning With Files

    OthmanAdi/planning-with-files

    Keeps a task plan, findings and progress log as Markdown files in the project so long multi-step agent work survives context resets.

    27k GitHub stars~3k tokensUpdated yesterday
    Agent WorkflowsAuto-check passed

  • Planning with Files for Kiro

    OthmanAdi/planning-with-files

    Keeps task_plan.md, findings.md and progress.md on disk as the agent's working memory for multi-step work, wired into Kiro steering, with no hooks.

    27k GitHub stars~2.1k tokensUpdated yesterday
    Agent WorkflowsAuto-check passed

  • Ultragoal Multi-Goal Ledger

    Yeachan-Heo/gajae-code

    Breaks a brief into ordered goals, keeps a durable ledger under .omc/ultragoal and prints handoff text so a Claude /goal run survives session restarts.

    2.9k GitHub stars~8.4k tokensUpdated today
    Agent WorkflowsAuto-check passed

  • File-Based Planning in Arabic

    OthmanAdi/planning-with-files

    Arabic edition of a file-based planning skill that keeps task_plan.md, findings.md and progress.md on disk so multi-step agent work survives lost context.

    27k GitHub stars~3.2k tokensUpdated yesterday
    Agent WorkflowsAuto-check: notes

More from CodeAlive-AI/ai-driven-development

All 22 skills in this repo

  • Investigating Repository History

    CodeAlive-AI/ai-driven-development

    Investigate GitHub repository history before risky code changes using git blame/log, GitHub PRs, review comments, squash/rebase/cherry-pick/rename heuristics, and cited evidence.

    155 GitHub stars~2k tokensUpdated yesterday
    Auto-check passed

  • Plugins Management

    CodeAlive-AI/ai-driven-development

    Create, publish, delete, and submit plugins for coding agents (Claude Code, OpenCode, Devin CLI/Desktop).

    155 GitHub stars~3.1k tokensUpdated yesterday
    Auto-check: notes

  • Semantic Scholar Deep

    CodeAlive-AI/ai-driven-development

    Deep research over the Semantic Scholar Graph API. An agent skill from CodeAlive-AI/ai-driven-development.

    155 GitHub starsUsed in 1 repo~2.2k tokens
    Auto-check passed

  • Windows QA Engineer

    CodeAlive-AI/ai-driven-development

    A skill your agent uses when testing Windows 11 desktop apps (WinForms/WPF/UWP) via UFO UIA/Win32 automation MCP.

    155 GitHub stars~1.4k tokensUpdated yesterday
    Auto-check passed

  • Agentic Readiness

    CodeAlive-AI/ai-driven-development

    Audit and improve repositories for reliable agentic work across Codex and Codex App, Claude Code, and OpenCode.

    155 GitHub stars~1.2k tokensUpdated yesterday
    Auto-check passed

  • Hooks Management

    CodeAlive-AI/ai-driven-development

    Manage hooks and automation for coding agents (Claude Code, Codex CLI, OpenCode, Devin CLI/Desktop).

    155 GitHub stars~4.8k tokensUpdated yesterday
    Auto-check: notes

Categories

Questions about Fpf Problem Solving

What does Fpf Problem Solving do?

Use First Principles Framework (FPF) to decompose problems, architect systems, evaluate alternatives, define quality, recover and replace methods, initiate inquiry from ordinary work, disambiguate…. Fpf Problem Solving is an agent skill from CodeAlive-AI/ai-driven-development.

When should I use Fpf Problem Solving?

Fpf Problem Solving fits situations like: tasks that involve Domain-driven design; tasks that involve Planning; tasks that involve Session handoff.

How do I install Fpf Problem Solving in Claude Code?

Run `npx skills add CodeAlive-AI/ai-driven-development --skill fpf-problem-solving -a claude-code`. Or copy the skill folder (skills/fpf-problem-solving in CodeAlive-AI/ai-driven-development) into .claude/skills/fpf-problem-solving in your project. Claude Code loads it when a task matches its description.

How do I install Fpf Problem Solving in Codex?

Run `npx skills add CodeAlive-AI/ai-driven-development --skill fpf-problem-solving -a codex`. Or copy the skill folder (skills/fpf-problem-solving in CodeAlive-AI/ai-driven-development) into .agents/skills/fpf-problem-solving in your project. Codex loads it when a task matches its description.

Can I use Fpf Problem Solving in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add CodeAlive-AI/ai-driven-development --skill fpf-problem-solving -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/fpf-problem-solving, .gemini/skills/fpf-problem-solving, .github/skills/fpf-problem-solving and .opencode/skills/fpf-problem-solving in your project.

What does Fpf Problem Solving need to run?

Going by SKILL.md and its folder, Fpf Problem Solving needs Python for the scripts in its folder. Our summary lists: Python 3.

Does Fpf Problem Solving access the network?

SKILL.md names 2 domains. As links in the text: github.com and creativecommons.org. This is read from the text; nothing was executed.

Is Fpf Problem Solving safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. The check reads SKILL.md only: the scripts in the folder are not scanned, so read them before running anything.

What licence does Fpf Problem Solving use?

Fpf Problem Solving is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Fpf Problem Solving use?

About 6.6k tokens (SKILL.md is roughly 27k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Fpf Problem Solving?

Skills that share tags, products or a category with Fpf Problem Solving: Planning with Files (OthmanAdi/planning-with-files, 27k stars), Using LWC Memory and Graphs (sickn33/agentic-awesome-skills, 47k stars), Planning With Files (OthmanAdi/planning-with-files, 27k stars) and Planning with Files for Kiro (OthmanAdi/planning-with-files, 27k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Fpf Problem Solving?

CodeAlive-AI (a GitHub organization) maintains it in CodeAlive-AI/ai-driven-development, which has 155 GitHub stars. The repository holds 22 skills in this directory. The repository was last updated on October 6, 2026.

Source: CodeAlive-AI/ai-driven-development on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.