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

Ten-Stage Think Loop

by AgriciDaniel in AgriciDaniel/claude-obsidian

Walks a consequential decision through ten reasoning stages, separating observed facts from inferences and unknowns, and stays read-only throughout.

MITAuto-check passedAgent Workflows

Install Ten-Stage Think Loop

skills CLI
$ npx skills add AgriciDaniel/claude-obsidian --skill think -a claude-code

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

GitHub CLI
$ gh skill install AgriciDaniel/claude-obsidian think --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/AgriciDaniel/claude-obsidian.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/think .claude/skills/think && 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
think
GitHub stars
15k
Token cost
~1.2k tokens
SKILL.md length
548 words
Files
1
Skills in repo
15
Repo updated
First seen
Licence
MIT

At a glance

Walks a consequential decision through ten reasoning stages, separating observed facts from inferences and unknowns, and stays read-only throughout.

  • Works in 10 steps: OBSERVE — external → OBSERVE — internal → LISTEN → …
  • Reviewing an architecture choice that has real tradeoffs
  • SKILL.md covers Establish an evidence frame, The ten stages, Verification discipline and Output shape
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

For ambiguous or high-stakes questions such as architecture reviews, postmortems and tradeoff analysis, the agent first sorts what it knows into observed, inferred, unknown and preference. It then runs a loop that moves from observing external facts and its own biases, through listening for intent and constraints, to thinking about alternatives, connecting laterally and across the system, and considering the human impact. The depth scales with novelty, stakes, uncertainty and irreversibility.

The skill is read-only. It can inspect evidence but does not edit files, change a vault, commit to Git or publish anything. If the create stage recommends a change, the agent hands off to a separate mutation skill after you approve. It never invents quotations, test results or confidence levels, and it is meant for reasoning review rather than vault health checks or repairs.

When your agent uses it

  • Reviewing an architecture choice that has real tradeoffs
  • Running a postmortem on an outage or a project that went wrong
  • Challenging the assumptions behind a plan before committing to it
  • Making a decision that would be costly to reverse

Example prompts

  • “Think this through: should we split billing out of the monolith or keep it in one deploy?”
  • “Do a deep think on why the last release slipped and what we are assuming about the cause.”
  • “Challenge my assumptions about moving the research notes into a new folder structure.”

Workflow steps

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

  1. OBSERVE — external
  2. OBSERVE — internal
  3. LISTEN
  4. THINK
  5. CONNECT — lateral
  6. CONNECT — system
  7. FEEL
  8. ACCEPT
  9. CREATE
  10. GROW

What it can do on your machine

Read from SKILL.md and the folder at commit 32ac5a0. 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

    No scripts in the folder and no shell commands in SKILL.md (its code samples are markdown).

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

  • Network

    No URLs in SKILL.md.

    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

Ten-Stage Think Loop loads about 1.2k tokens when it runs. Until then it costs about 96 tokens; SKILL.md has 548 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~96
When it runs · the whole SKILL.md, loaded when a task matches
~1.2k

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); files beside SKILL.md are not scanned.

SKILL.md

The full file from AgriciDaniel/claude-obsidian at commit 32ac5a0, republished under its MIT licence (© AgriciDaniel). 548 words, ~1,165 tokens.

Download SKILL.mdSave it as .claude/skills/think/SKILL.md (or your agent's skills folder).
name
think
description
Apply the Fable-derived 10-stage OBSERVE, OBSERVE, LISTEN, THINK, CONNECT, CONNECT, FEEL, ACCEPT, CREATE, GROW loop to consequential or ambiguous reasoning and decisions. Use for think this through, deep think, architecture review, postmortem, tradeoff analysis, or challenges to assumptions. This is a reasoning review, not a deterministic vault health check or repair workflow.

Think

Use the ten stages as a loop of attention, not a ceremonial transcript. Scale the depth to novelty, stakes, uncertainty, and irreversibility. Keep the final reasoning summary concise and evidence-bearing.

This skill is read-only. It may inspect available evidence, but it does not edit files, execute a vault mutation, commit Git, or publish anything. If the CREATE stage recommends a change, compose with the appropriate mutation skill after the user authorizes that operation.

Establish an evidence frame

Before the loop, separate:

  • Observed: directly supported by an input, source, test, or measurement.
  • Inferred: a conclusion drawn from observations; state the bridge.
  • Unknown: missing evidence that could change the decision.
  • Preference: a user or designer choice, not a factual claim.

Attach citations or concrete locators when sources exist. Never fabricate a quotation, locator, test result, consensus, or confidence level.

The ten stages

1. OBSERVE — external

Read the actual inputs, current state, constraints, failures, and prior work. Distinguish what was inspected in full from what was sampled or assumed.

2. OBSERVE — internal

Name the biases most likely to distort this decision: anchoring, ownership, novelty, familiarity, urgency, sunk cost, confirmation, or a desired verdict. Recalibrate confidence to the evidence available.

3. LISTEN

Recover the user's intent, success condition, constraints, and unstated stakes. Attend to error messages, dissent, edge cases, and affected voices. Ask only questions whose answers could materially change the outcome.

4. THINK

Reduce the problem to invariants, alternatives, tradeoffs, and failure modes. Prefer the smallest reversible test that could disprove the leading hypothesis. Treat failure behavior as part of the specification.

5. CONNECT — lateral

Look for the same structure in adjacent components or another domain. Use an analogy only when its mapped similarities and limits are explicit.

6. CONNECT — system

Trace upstream inputs, downstream consumers, ownership, state boundaries, interfaces, and recovery paths. Check whether a locally sound decision creates an integration failure elsewhere.

7. FEEL

Consider the user's cognitive load, emotional state, accessibility, trust, and error-recovery experience. Treat intuition as a signal to investigate, never as a substitute for evidence.

Show full SKILL.md (209 more words)Show less
8. ACCEPT

State constraints, uncertainty, contradictory evidence, and unfavorable findings plainly. Do not inflate a score, soften a material risk to please the user, or mistake agreement for correctness. Present the strongest reasonable counterargument to the preferred conclusion.

9. CREATE

Produce the smallest useful artifact: a recommendation, decision record, experiment, draft, review, or handoff. Mark assumptions and unresolved risks. Do not mutate state under this skill.

10. GROW

Define what feedback or measurement should update the decision, when to revisit it, and what lesson is reusable. Saving the lesson is a separate explicit operation composed with save.

Verification discipline

Before calling the work complete:

  1. Test the highest-risk claim or clearly state why it remains untested.
  2. Seek disconfirming evidence, not only supporting examples.
  3. Match verification effort to blast radius and reversibility.
  4. Report actual commands, sources, artifacts, or observations used.
  5. Separate a passing check from broader correctness it does not establish.
  6. Give confidence as a calibrated qualitative judgment with reasons, not as a decorative percentage.

Output shape

Adapt the headings to the task, but preserve these outcomes:

markdown
## Decision
<recommendation or artifact>

## Evidence
<observed facts and important inferences>

## Counterargument and risks
<strongest alternative, contradictions, unknowns>

## Verification
<checks performed and checks still needed>

## Growth loop
<feedback signal, revisit condition, reusable lesson>

For a trivial, reversible lookup or typo, skip the formal loop. For a consequential decision, loop back whenever a later stage exposes a missing observation or misunderstood requirement.

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

Files

Just SKILL.md in skills/think of AgriciDaniel/claude-obsidian.

Open the folder on GitHubat commit 32ac5a0

Compare with similar skills

Ten-Stage Think Loop 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.

Ten-Stage Think Loop compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Ten-Stage Think Loop this skillAgriciDaniel/claude-obsidian15k—~1.2kAutomated safety check: PassMIT
Design Firstrohitg00/skillkit1.5k—~1.5kAutomated safety check: PassApache-2.0
Solution ArchitectIBM/ibm-watsonx-orchestrate-adk178—~8.4kAutomated safety check: PassMIT
Audit Flowzebbern/claude-code-guide4.6k—~4.2kAutomated safety check: PassMIT
Think: Plan Before You Buildtw93/Waza7.2k—~3kAutomated safety check: NotesMIT
Architect Before Implementingcursor/plugins10k8 repos~1.4kAutomated safety check: PassNone

Similar skills

  • Design First

    rohitg00/skillkit

    Guides the creation of technical design documents before writing code, producing architecture diagrams, data models, API interface definitions, implementation plans, and multi-option trade-off…

    1.5k GitHub stars~1.5k tokensUpdated 4 mo ago
    Agent WorkflowsAuto-check passed

  • Solution Architect

    IBM/ibm-watsonx-orchestrate-adk

    Official

    Expert guidance for creating high-level solution architecture documents from business requirements, use cases, or problem statements.

    178 GitHub stars~8.4k tokensUpdated 4 days ago
    Agent WorkflowsAuto-check passed

  • Audit Flow

    zebbern/claude-code-guide

    Interactive system flow tracing across CODE, API, AUTH, DATA, NETWORK layers with SQLite persistence and Mermaid export.

    4.6k GitHub stars~4.2k tokensUpdated today
    DevelopmentAuto-check passed

  • Think: Plan Before You Build

    tw93/Waza

    Turns a rough idea into an approved, decision-complete plan or recommendation before any code is written, for architecture choices and go or no-go calls.

    7.2k GitHub stars~3k tokensUpdated today
    DevelopmentAuto-check: notes

  • Architect Before Implementing

    cursor/plugins

    Official

    Sketches types, signatures and module boundaries with stub bodies before real code, compares at least two designs, then implements against the chosen sketch.

    10k GitHub starsUsed in 8 repos~1.4k tokens
    DevelopmentAuto-check passed

  • SPARC Methodology

    ruvnet/agentic-flow

    Structures complex feature work into five planning-first phases (specification, pseudocode, architecture, refinement and completion) driven through claude-flow commands.

    816 GitHub starsUsed in 6 repos~6.3k tokens
    DevelopmentAuto-check passed

More from AgriciDaniel/claude-obsidian

All 15 skills in this repo

  • Bounded Autoresearch

    AgriciDaniel/claude-obsidian

    Runs a bounded, source-grounded research loop that drafts a cited dossier and can propose a separately reviewed merge into an Obsidian vault.

    15k GitHub stars~1.6k tokensUpdated 27 days ago
    Auto-check passed

  • Obsidian Canvas Boards

    AgriciDaniel/claude-obsidian

    Creates, inspects and updates Obsidian JSON Canvas boards in a vault, with text, file, link, group and edge nodes, using safe recoverable edits.

    15k GitHub stars~1.4k tokensUpdated 27 days ago
    Auto-check passed

  • Obsidian Wiki Vault Setup

    AgriciDaniel/claude-obsidian

    Sets up or adopts a separate Obsidian knowledge vault through the claude-obsidian core script and routes follow-up work to the right wiki sub-skill.

    15k GitHub stars~1.3k tokensUpdated 27 days ago
    Auto-check passed

  • Obsidian Wiki Log Fold

    AgriciDaniel/claude-obsidian

    Creates a bounded, extractive rollup of recent Obsidian wiki log entries, previewed by default, with one optional apply step and no changes to child pages.

    15k GitHub stars~1.2k tokensUpdated 27 days ago
    Auto-check passed

  • Defuddle Web Page Cleaner

    AgriciDaniel/claude-obsidian

    Plans, and with explicit network consent runs, an external Defuddle extractor that turns an article-like HTTPS page into clean Markdown for later wiki ingestion.

    15k GitHub stars~1.1k tokensUpdated 27 days ago
    Auto-check passed

  • Obsidian Bases Editor

    AgriciDaniel/claude-obsidian

    Explains, drafts and validates Obsidian Bases .base files, building filters, formulas and table, card or list views, and applying edits only through one inspected transaction.

    15k GitHub stars~1.2k tokensUpdated 27 days ago
    Auto-check passed

Categories

Questions about Ten-Stage Think Loop

What does Ten-Stage Think Loop do?

Walks a consequential decision through ten reasoning stages, separating observed facts from inferences and unknowns, and stays read-only throughout. For ambiguous or high-stakes questions such as architecture reviews, postmortems and tradeoff analysis, the agent first sorts what it knows into observed, inferred, unknown and preference. It then runs a loop that moves from observing external facts and its own biases, through listening for intent and constraints, to thinking about alternatives, connecting laterally and across the system, and considering the human impact.

When should I use Ten-Stage Think Loop?

Ten-Stage Think Loop fits situations like: reviewing an architecture choice that has real tradeoffs; running a postmortem on an outage or a project that went wrong; challenging the assumptions behind a plan before committing to it; making a decision that would be costly to reverse.

How do I install Ten-Stage Think Loop in Claude Code?

Run `npx skills add AgriciDaniel/claude-obsidian --skill think -a claude-code`. Or copy the skill folder (skills/think in AgriciDaniel/claude-obsidian) into .claude/skills/think in your project. Claude Code loads it when a task matches its description.

How do I install Ten-Stage Think Loop in Codex?

Run `npx skills add AgriciDaniel/claude-obsidian --skill think -a codex`. Or copy the skill folder (skills/think in AgriciDaniel/claude-obsidian) into .agents/skills/think in your project. Codex loads it when a task matches its description.

Can I use Ten-Stage Think Loop 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 AgriciDaniel/claude-obsidian --skill think -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/think, .gemini/skills/think, .github/skills/think and .opencode/skills/think in your project.

What does Ten-Stage Think Loop need to run?

SKILL.md names no scripts, command-line tools or credentials: Ten-Stage Think Loop is instructions for the agent only.

Does Ten-Stage Think Loop access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Ten-Stage Think Loop 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. Review the folder before installing.

What licence does Ten-Stage Think Loop use?

Ten-Stage Think Loop 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 Ten-Stage Think Loop use?

About 1.2k tokens (SKILL.md is roughly 4.7k 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 Ten-Stage Think Loop?

Skills that share tags, products or a category with Ten-Stage Think Loop: Design First (rohitg00/skillkit, 1.5k stars), Solution Architect (IBM/ibm-watsonx-orchestrate-adk, 178 stars), Audit Flow (zebbern/claude-code-guide, 4.6k stars) and Think: Plan Before You Build (tw93/Waza, 7.2k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Ten-Stage Think Loop?

AgriciDaniel (a GitHub user) maintains it in AgriciDaniel/claude-obsidian, which has 15,379 GitHub stars. The repository holds 15 skills in this directory. The repository was last updated on September 10, 2026.

Source: AgriciDaniel/claude-obsidian on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.