Agent skill

Absolute Spec

by maddhruv in maddhruv/absolute

Lightweight standalone design spec for AI coding agents: codebase scan → bounded clarify pass (3–5 questions, not a grill) → reviewed design doc written to docs/plans/ → independent scored review →…

MITAuto-check passedDevelopment

Install Absolute Spec

skills CLI
$ npx skills add maddhruv/absolute --skill absolute-spec -a claude-code

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

GitHub CLI
$ gh skill install maddhruv/absolute absolute-spec --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/maddhruv/absolute.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/absolute-spec .claude/skills/absolute-spec && 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
absolute-spec
GitHub stars
218
Used in
1 other repo
Token cost
~2.3k tokens
SKILL.md length
1,162 words
Files
2
Skills in repo
10
Repo updated
First seen
Licence
MIT

At a glance

Lightweight standalone design spec for AI coding agents: codebase scan → bounded clarify pass (3–5 questions, not a grill) → reviewed design doc written to docs/plans/ → independent scored review →…

  • Works in 5 steps: SCAN → CLARIFY (bounded pass) → WRITE → …
  • You want a spec to discuss
  • SKILL.md covers Absolute Spec, When to use this command, Key Principles and The Flow, plus 3 more sections
  • Calls git

What it does

Absolute Spec is an agent skill from maddhruv/absolute. Lightweight standalone design spec for AI coding agents: codebase scan → bounded clarify pass (3–5 questions, not a grill) → reviewed design doc written to docs/plans/ → independent scored review → stop. No task board, no build. Use when you want a spec to discuss, hand off, or review before committing to implementation. Chains into absolute-work when ready to build. Triggers on "absolute spec", "write a spec", "spec out this feature", "draft a design doc", "I want a spec to hand off / review, don't build it yet".

Its SKILL.md is about 2.3k tokens, which your agent loads only when the skill is triggered. The skill folder holds 1 other file (for example `README.md`).

It sits in Development, covering Architecture decision records. The repository describes itself as: Absolute Skills to 10x your Development Lifecycle. The licence is MIT.

When your agent uses it

  • You want a spec to discuss
  • Review before committing to implementation
  • Spec out this feature
  • Draft a design doc

Example prompts

  • “absolute spec”
  • “write a spec”
  • “spec out this feature”
  • “/absolute-spec”

Workflow steps

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

  1. SCAN
  2. CLARIFY (bounded pass)
  3. WRITE
  4. REVIEW (scored, independent)
  5. HANDOFF

What it can do on your machine

Read from SKILL.md and the folder at commit 2166274. 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

    Shell commands in SKILL.md call:

    • git

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

  • Network

    No URLs in SKILL.md. Its commands use git, which can reach the network depending on how they are called.

    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

Absolute Spec loads about 2.3k tokens when it runs. Until then it costs about 133 tokens; SKILL.md has 1,162 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~133
When it runs · the whole SKILL.md, loaded when a task matches
~2.3k

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 maddhruv/absolute at commit 2166274, republished under its MIT licence (© maddhruv). 1,162 words, ~2,277 tokens.

Download SKILL.mdSave it as .claude/skills/absolute-spec/SKILL.md (or your agent's skills folder). This skill also uses 1 other file; get the full folder from GitHub.
name
absolute-spec
description
Lightweight standalone design spec for AI coding agents: codebase scan → bounded clarify pass (3–5 questions, not a grill) → reviewed design doc written to docs/plans/ → independent scored review → stop. No task board, no build. Use when you want a spec to discuss, hand off, or review before committing to implementation. Chains into absolute-work when ready to build. Triggers on "absolute spec", "write a spec", "spec out this feature", "draft a design doc", "I want a spec to hand off / review, don't build it yet".
version
0.5.0
category
workflow
tags
workflow, spec, specification, planning, design
platforms
claude-code, gemini-cli, openai-codex, mcp
user-invocable
true
argument-hint
[target]
license
MIT

Start your first response with the 📋 emoji.

Absolute Spec

Absolute Spec turns a fuzzy intent into a reviewed design-spec document — then stops. It is the planning artifact of work, lifted out of the full lifecycle: scan the codebase, ask only the questions the code can't answer, write the spec, run an independent scored review, and hand back a doc you can discuss, hand off, or feed into /absolute work to build.

It is deliberately lightweight. No relentless interview, no task board, no decompose, no execution. One deliverable: a spec good enough that an unfamiliar developer could build from it.


When to use this command

Use spec when:

  • You want a design spec to discuss, review, or hand off — not build right now.
  • You need to think a feature through on paper before committing to implementation.
  • A teammate or another agent will do the building from your spec.
  • You want a fast, reviewed design doc without the full phase-gated lifecycle.

Do NOT use spec when:

  • You want to design AND build in one flow → use /absolute work (spec is its Phase 2, followed by decompose + safe-wave execution).
  • You're documenting code that already exists / already shipped → use /absolute docs (reference/explanation docs, not a forward design).
  • The change is a one-line obvious fix needing no design.

The line vs work: spec produces a doc and stops; work produces a doc and then builds it. If you're unsure whether you'll build it now, start with spec — you can chain into work afterward and it will pick the spec up.


Key Principles

  1. Codebase before questions. Read what exists first; ask only what code can't answer.
  2. Bounded, not relentless. A short clarify pass (3–5 questions), not the depth-first grill work runs. Batching questions is fine.
  3. The spec is the deliverable. Quality matters more here than anywhere — keep the independent scored review.
  4. Reuse, don't reinvent. Template, scaling rules, and review rubric come from absolute-work's references/spec-writing.md. This command is the thin flow around them.
  5. Stop after review. No code, no board, no execution. Hand off cleanly.
  6. Never auto-commit. Write the spec file and report; the user commits.

The Flow

SCAN ─→ CLARIFY ─→ WRITE ─→ REVIEW ─→ HANDOFF

No hard gates between steps (that's work). The one checkpoint is the clarify pass — ask, get answers, then proceed straight through to a reviewed spec.


Step 1 — SCAN

Ground the spec in reality before asking anything.

  1. Convention detection — read cached config first: if .absolute.config.json or ~/.absolute/config.json exists (from /absolute init), resolve the effective config (project file → global projects["<cwd>"] → global defaults) and use its conventions, detecting only what's missing. No config → soft-suggest init and run work's Codebase Convention Detection table (package manager, language/runtime, test runner, linter, build system, directory conventions; see absolute-work's SKILL.md under Codebase Convention Detection). The spec must speak the project's real stack, scripts, and paths.
  2. Deep context scan — read what exists: docs/ (README first), root README.md, CLAUDE.md, CONTRIBUTING.md, docs/plans/ (overlapping/related designs), recent commits (last 10–20), package manifests, and the directories the feature touches.
  3. Synthesize — state what you learned in 2–4 lines (stack, relevant existing code, any overlapping prior design). Do not dump a file listing.

Detect the work type (feature / refactor / greenfield / migration) only enough to shape the spec — spec does not run the full per-type question banks.


Step 2 — CLARIFY (bounded pass)

Ask only the questions the codebase genuinely cannot answer — the preference and scope forks. Cap at 3–5 questions; batching is allowed (one AskUserQuestion call with multiple questions where available).

Good questions to ask (when code can't answer them):

  • Scope boundary — what's in v1 vs explicitly deferred.
  • Behavior forks — real-time vs batch, sync vs async, the genuine "which way" decisions.
  • Data/contract shape — only where the design hinges on it and code gives no signal.
  • Non-goals — what this explicitly will NOT do.

Do NOT ask: anything a config, manifest, test file, or existing pattern already states. When the code answers it, say so in the spec instead of asking.

If the user said "no questions, just draft it" — skip to WRITE and capture every guess in an ## Open Questions / assumptions section instead.


Show full SKILL.md (487 more words)Show less
Step 3 — WRITE

Write the spec to <specDir>/YYYY-MM-DD-<topic>-design.md (<topic> = short kebab-case slug). <specDir> is preferences.specDir from config when present, else docs/plans.

Use the template, section-scaling rules, writing style, and Decision Log format from absolute-work's references/spec-writing.md — that file is the single source of truth; do not restate it here, load it. In particular:

  • Pick the complexity tier (Simple / Medium / Complex) using the complexity heuristic table, and scale sections accordingly. Remove sections that would only say "N/A".
  • Be concrete: real file paths, real endpoints, real schemas in code blocks — never "an endpoint for X".
  • Fill the Decision Log with the forks resolved in CLARIFY plus any you recommended, each with a one-line rationale.

Step 4 — REVIEW (scored, independent)

Dispatch a separate reviewer subagent — the agent that wrote the spec does not grade it (generator ≠ evaluator). Use the rubric and reviewer prompt template verbatim from absolute-work's references/spec-writing.md (Scored Spec Review Protocol): graded on Completeness, Consistency, Clarity, Scope, Testability (1–5 each, weighted).

Weighted ScoreVerdictAction
4.0 – 5.0ApprovedProceed to HANDOFF
3.0 – 3.9Needs WorkFix the flagged issues, re-dispatch (max 3 iterations)
< 3.0Major GapsSurface to the user immediately; do not silently iterate

Reviewer approval is necessary but not the end — the user still has the final say at HANDOFF.


Step 5 — HANDOFF
  1. Present — the spec path, the complexity tier, and the reviewer's weighted score + verdict. Summarize the key decisions in 2–4 lines.
  2. Offer to build — chain into /absolute work, which will pick up the spec at its decompose phase rather than re-running intake. Make this an explicit, optional next step.
  3. Stop. No code, no board. Never run git commit — suggest a message if asked; the user commits.

Gotchas

  1. Drifting into work. If you start decomposing into tasks or writing code, you've left spec. Stop at the reviewed doc.
  2. Asking what the code answers. The bounded pass is for preferences and forks only — scan first, ask second.
  3. Skipping the review to "stay light". The review is the cheap quality gate that makes a standalone spec trustworthy. Keep it.
  4. Restating spec-writing.md. Load it; don't copy the template/rubric in here — two copies drift.
  5. Over-asking. More than ~5 questions means you're running work's interview. Tighten.

Output / Response Style

Respond terse like smart caveman. All technical substance stay. Only fluff die. Drop articles, filler, pleasantries, hedging. Fragments OK. Technical terms exact. Code blocks and quoted errors unchanged. Drop caveman for security warnings, irreversible-action confirmations, and any multi-step sequence where fragment order risks misread; resume after. Spec prose itself is written normally (it's a deliverable, not chat).


Companion commands

Sibling commands in this skill chain naturally around spec:

  • /absolute work — build what the spec describes (picks the spec up at decompose).
  • /absolute ui — design the interface for a feature the spec defines.
  • /absolute docs — once it's built and shipped, document it for readers.

Suggest them where relevant; they're always available (same skill, no extra install).

© maddhruv, 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 1 other file in skills/absolute-spec of maddhruv/absolute.

  • SKILL.md
  • README.md

Open the folder on GitHubat commit 2166274

Used in 1 other repository

We found 1 copy of this SKILL.md (exact, near-identical or edited) in other folders, from 1 other GitHub owner. This page covers the copy in maddhruv/absolute, which our catalogue first saw on October 7, 2026.

Compare with similar skills

Absolute Spec 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.

Absolute Spec compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Absolute Spec this skillmaddhruv/absolute2181 repos~2.3kAutomated safety check: PassMIT
PR Design DocOpenHands/OpenHands90k—~2.4kAutomated safety check: PassMIT
Cto AdvisorIbrahim-3d/orchestrator-supaconductor3804 repos~2.4kAutomated safety check: PassMIT
Improve Codebase Architectureywwynm/EverythingDone14415 repos~1.3kAutomated safety check: PassGPL-3.0
Domain Modelingbrim-borium/spotify_sdk1665 repos~806Automated safety check: PassApache-2.0
Design Doc MermaidSpillwaveSolutions/design-doc-mermaid1751 repos~5.6kAutomated safety check: PassNone

Similar skills

  • PR Design Doc

    OpenHands/OpenHands

    For a non-trivial pull request, write a self-contained HTML design doc under the temporary .pr/ directory and link a visibility-appropriate preview in the PR description, so maintainers grasp the…

    90k GitHub stars~2.4k tokensUpdated today
    DevelopmentAuto-check passed
  • Cto Advisor

    Ibrahim-3d/orchestrator-supaconductor

    Technical leadership guidance for engineering teams, architecture decisions, and technology strategy.

    380 GitHub starsUsed in 4 repos~2.4k tokens
    DevelopmentAuto-check passed
  • Improve Codebase Architecture

    ywwynm/EverythingDone

    Find deepening opportunities in a codebase, informed by the domain language in CONTEXT.md and the decisions in docs/adr/.

    144 GitHub starsUsed in 15 repos~1.3k tokens
    DevelopmentAuto-check passed
  • Domain Modeling

    brim-borium/spotify_sdk

    Build and sharpen a project's domain model. An agent skill from brim-borium/spotify_sdk.

    166 GitHub starsUsed in 5 repos~806 tokens
    DevelopmentAuto-check passed
  • Design Doc Mermaid

    SpillwaveSolutions/design-doc-mermaid

    Create Mermaid diagrams (flowchart, sequence, class, ER, state, C4, architecture) from text or source code.

    175 GitHub starsUsed in 1 repo~5.6k tokens
    DevelopmentAuto-check passed
  • Learning Opportunities

    DrCatHicks/learning-opportunities

    Facilitates deliberate skill development during AI-assisted coding.

    2.5k GitHub stars~2.5k tokensUpdated 1 mo ago
    DevelopmentAuto-check passed

More from maddhruv/absolute

All 10 skills in this repo
  • Absolute Init

    maddhruv/absolute

    One-time setup for absolute: interview how you want it to behave (output style, autonomy, TDD strictness, spec dir, families) + detect the stack once, then write .absolute.config.json (project…

    218 GitHub starsUsed in 1 repo~3k tokens
    Auto-check passed
  • Absolute Audit

    maddhruv/absolute

    Vulnerability and security scan (defensive, your own repo): dependency CVEs plus risky code patterns (secrets, injection, weak authz), severity x reachability triaged and remediated without…

    218 GitHub starsUsed in 1 repo~1.2k tokens
    Auto-check passed
  • Absolute Simplify

    maddhruv/absolute

    A skill your agent uses when the user wants to simplify, clean up, refactor, tidy, or refine code — their staged/unstaged git changes or a target file/path.

    218 GitHub stars~6.1k tokensUpdated 3 mo ago
    Auto-check passed
  • Absolute Debt

    maddhruv/absolute

    Lint and typecheck debt paydown: clear pre-existing repo-wide lint/type violations and suppressions (@ts-ignore, type: ignore) one rule per wave, fixing causes not symptoms.

    218 GitHub starsUsed in 1 repo~1.1k tokens
    Auto-check passed
  • Absolute Work

    maddhruv/absolute

    End-to-end, phase-gated SDLC for AI coding agents: relentless design interview → reviewed spec → dependency-graphed task board → safe-wave TDD execution → verification → converge.

    218 GitHub stars~5.3k tokensUpdated 3 mo ago
    Auto-check passed
  • Absolute Deflake

    maddhruv/absolute

    Flaky test fixes: detect nondeterministic tests empirically (repeat/shuffle/parallel runs), diagnose the root cause, fix it — never retry/skip/sleep — and verify across many randomized runs.

    218 GitHub starsUsed in 1 repo~1.2k tokens
    Auto-check passed

Categories

Questions about Absolute Spec

What does Absolute Spec do?

Lightweight standalone design spec for AI coding agents: codebase scan → bounded clarify pass (3–5 questions, not a grill) → reviewed design doc written to docs/plans/ → independent scored review →…. Absolute Spec is an agent skill from maddhruv/absolute. Lightweight standalone design spec for AI coding agents: codebase scan → bounded clarify pass (3–5 questions, not a grill) → reviewed design doc written to docs/plans/ → independent scored review → stop.

When should I use Absolute Spec?

Absolute Spec fits situations like: you want a spec to discuss; review before committing to implementation; spec out this feature; draft a design doc.

How do I install Absolute Spec in Claude Code?

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

How do I install Absolute Spec in Codex?

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

Can I use Absolute Spec 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 maddhruv/absolute --skill absolute-spec -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/absolute-spec, .gemini/skills/absolute-spec, .github/skills/absolute-spec and .opencode/skills/absolute-spec in your project.

What does Absolute Spec need to run?

Going by SKILL.md and its folder, Absolute Spec needs the command-line tools its instructions call (git).

Does Absolute Spec access the network?

SKILL.md contains no URLs. Its commands use git, which can reach the network depending on how they are called. This is read from the text; nothing was executed.

Is Absolute Spec 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 Absolute Spec use?

Absolute Spec is published under the MIT licence (declared in SKILL.md). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Absolute Spec use?

About 2.3k tokens (SKILL.md is roughly 9.1k 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 Absolute Spec?

Skills that share tags, products or a category with Absolute Spec: PR Design Doc (OpenHands/OpenHands, 90k stars), Cto Advisor (Ibrahim-3d/orchestrator-supaconductor, 380 stars), Improve Codebase Architecture (ywwynm/EverythingDone, 144 stars) and Domain Modeling (brim-borium/spotify_sdk, 166 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Absolute Spec?

maddhruv (a GitHub user) maintains it in maddhruv/absolute, which has 218 GitHub stars. The repository holds 10 skills in this directory. The repository was last updated on July 6, 2026.

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