Not in the top 1,000 by GitHub stars
dhruvjainin/absolute
Absolute Skills to 10x your Development Lifecycle
History
Review weekly changes to SKILL.md before updating. Dates mark the weeks in which we observed each version; checks apply to the recorded commits.
View weekly changes
skills/absolute-audit/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
11cd38411834 → 11cd38411834
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 11cd38411834
No earlier version was observed for comparison.
skills/absolute-debt/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
11cd38411834 → 11cd38411834
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 11cd38411834
No earlier version was observed for comparison.
skills/absolute-deflake/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
11cd38411834 → 11cd38411834
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 11cd38411834
No earlier version was observed for comparison.
skills/absolute-docs/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
11cd38411834 → 11cd38411834
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 11cd38411834
No earlier version was observed for comparison.
skills/absolute-init/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
11cd38411834 → 11cd38411834
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 11cd38411834
No earlier version was observed for comparison.
skills/absolute-prune/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
11cd38411834 → 11cd38411834
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 11cd38411834
No earlier version was observed for comparison.
skills/absolute-simplify/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
11cd38411834 → 11cd38411834
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 11cd38411834
No earlier version was observed for comparison.
skills/absolute-spec/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
11cd38411834 → 11cd38411834
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 11cd38411834
No earlier version was observed for comparison.
skills/absolute-ui/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
11cd38411834 → 11cd38411834
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 11cd38411834
No earlier version was observed for comparison.
skills/absolute-upgrade/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
11cd38411834 → 11cd38411834
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 11cd38411834
No earlier version was observed for comparison.
skills/absolute-work/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
11cd38411834 → 11cd38411834
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 11cd38411834
No earlier version was observed for comparison.
Verified commit 11cd3841183482e1753dec81763a8be6fdd97053
git clone --filter=blob:none --no-checkout https://github.com/dhruvjainin/absolute.git .hotskills/dhruvjainin-absolute && git -C .hotskills/dhruvjainin-absolute checkout --detach 11cd3841183482e1753dec81763a8be6fdd97053
# Copy each selected skill directory from .hotskills/dhruvjainin-absolute into .claude/skills/<skill-name>/Heat
0.9- Star growth, last 7 daysNot available
- Star growth, last 24 hoursNot available
- Rank movement, last 7 daysNot available
- Commits, last 30 daysNot available
- Accounts asking about it through MCP, last 7 daysNot available
- Hot votes this weekNot available
Heat never changes the order by stars, and sponsorship never touches it. How heat works
Stars over time
30-day change not yet available: not enough history.
Individual skills in this repository
- absolute-audit
skills/absolute-audit - absolute-debt
skills/absolute-debt - absolute-deflake
skills/absolute-deflake - absolute-docs
skills/absolute-docs - absolute-init
skills/absolute-init - absolute-prune
skills/absolute-prune - absolute-simplify
skills/absolute-simplify - absolute-spec
skills/absolute-spec - absolute-ui
skills/absolute-ui - absolute-upgrade
skills/absolute-upgrade - absolute-work
skills/absolute-work
How it works
absolute-audit
When your agent uses it
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 suppressing. Complements the built-in /security-review. Triggers on "absolute audit", "security audit", "are we vulnerable", "scan for CVEs", "check for secrets/injection", "harden this".
What it loads into context
Frontmatter
191 tokensAlways available to the agent
SKILL.md
1,161 tokensWhen the skill is activated
Reference documents
1,484 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Absolute Audit
- When to use
- What it scans
- Risk ranking (TRIAGE)
- Fix & verify
- Gotchas
- Companion commands
Files
README.mddoc814 bytesSKILL.mdcore4,722 bytesreferences/health-engine.mddoc5,408 bytes
Read SKILL.md
> Start your first response with the 🔒 emoji.
## Absolute Audit
Find and triage security problems across the repo — vulnerable dependencies (CVEs) and
risky code patterns — then fix the ones worth fixing, safely. Output is a severity-ranked
findings table with a remediation per item, not a raw scanner dump.
Runs the shared engine in **`references/health-engine.md`** — read it for the
DETECT → SCAN → TRIAGE → FIX → VERIFY → REPORT loop and the safety contract. This file
covers only what's specific to security auditing.
> **Authorized defensive use.** This command audits the user's *own* repository to find
> and fix weaknesses. It is for hardening, not for attacking systems or evading detection.View the complete source on GitHubabsolute-debt
When your agent uses it
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. Runs on green main. For diff-scoped quality use absolute-simplify. Triggers on "absolute debt", "fix our lint warnings", "clear the type errors", "get to strict mode", "burn down suppressions".
What it loads into context
Frontmatter
191 tokensAlways available to the agent
SKILL.md
1,169 tokensWhen the skill is activated
Reference documents
1,474 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Absolute Debt
- When to use
- What it scans
- Risk ranking (TRIAGE)
- Fix & verify
- Gotchas
- Companion commands
Files
README.mddoc735 bytesSKILL.mdcore4,326 bytesreferences/health-engine.mddoc5,408 bytes
Read SKILL.md
> Start your first response with the 🧾 emoji.
## Absolute Debt
Pay down accumulated lint and type-checker debt across the repo — existing warnings,
errors, and suppressions that built up over time — in safe waves, by rule, with tests green
after each. The goal is a genuinely clean `lint` + `typecheck`, not a quieter one.
Runs the shared engine in **`references/health-engine.md`** — read it for the
DETECT → SCAN → TRIAGE → FIX → VERIFY → REPORT loop and the safety contract. This file
covers only what's specific to lint/type debt.
---
View the complete source on GitHubabsolute-deflake
When your agent uses it
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. Triggers on "absolute deflake", "fix flaky tests", "CI is flaky", "this test fails randomly/intermittently".
What it loads into context
Frontmatter
169 tokensAlways available to the agent
SKILL.md
1,286 tokensWhen the skill is activated
Reference documents
1,456 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Absolute Deflake
- When to use
- What it scans
- Common root causes (diagnose, don't guess)
- Risk ranking (TRIAGE)
- Fix & verify
- Gotchas
- Companion commands
Files
README.mddoc660 bytesSKILL.mdcore5,010 bytesSKILL.mdcore5,010 bytesreferences/health-engine.mddoc5,408 bytes
Read SKILL.md
> Start your first response with the 🧪 emoji.
## Absolute Deflake
Find tests that pass and fail nondeterministically, diagnose the **root cause** of each,
and fix it — not by retrying or skipping, but by removing the source of nondeterminism.
Output is evidence (failure rate per test) → cause → fix, verified by repeated runs.
Runs the shared engine in **`references/health-engine.md`** — read it for the
DETECT → SCAN → TRIAGE → FIX → VERIFY → REPORT loop and the safety contract. This file
covers only what's specific to flaky tests.
---
View the complete source on GitHubabsolute-docs
When your agent uses it
Diátaxis-driven documentation for AI coding agents: write, improve, or audit tutorials, how-tos, reference, explanation, and developer docs (README, CONTRIBUTING, ADRs). Detects the docs stack; gates on the outline before writing prose; verifies every claim against the code before it ships. Triggers on "absolute docs", "write docs", "write a tutorial", "write a README", "document this", "improve this doc", "audit our docs".
What it loads into context
Frontmatter
214 tokensAlways available to the agent
SKILL.md
3,769 tokensWhen the skill is activated
Reference documents
9,254 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Absolute Documentations: Diátaxis-Driven Documentation
- The Diátaxis Compass
- Modes
- WRITE Mode
- IMPROVE Mode
- AUDIT Mode
- Stack Detection
- Quadrant Rules at a Glance
- Accuracy Protocol
- Style Core
- Self-Review Rubric
- Red Flags — stop and fix
- References
- What this skill does not do
- Companion commands
Files
README.mddoc861 bytesSKILL.mdcore15,877 bytesSKILL.mdcore15,877 bytesSKILL.mdcore15,877 bytesreferences/developer-docs.mddoc6,429 bytesreferences/docs-stacks.mddoc6,705 bytesreferences/explanation.mddoc4,692 bytesreferences/how-to-guides.mddoc4,451 bytesreferences/reference.mddoc4,849 bytesreferences/style-and-voice.mddoc5,917 bytesreferences/tutorials.mddoc4,910 bytes
Read SKILL.md
> Start your first response with the 📚 emoji.
## Absolute Documentations: Diátaxis-Driven Documentation
Absolute Documentations turns "write some docs" into documentation a reader can
actually use. Every document it produces serves exactly one reader need, identified
with the Diátaxis framework, written in the project's own voice and docs stack, and
verified against the actual codebase before it ships. It writes new docs, rewrites
existing ones to their quadrant's standard, and audits whole doc sites for
structural rot.
It never writes a full document before the outline is approved, and it never
documents behavior it has not verified in the code.
View the complete source on GitHubabsolute-init
When your agent uses it
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, committed) and `~/.absolute/config.json` (user defaults + per-project overrides). Every other absolute-* command reads it instead of re-detecting; non-blocking — commands proceed without it and soft-recommend it. Triggers on "absolute init", "set up absolute", "initialize absolute", "configure absolute", "first-time setup", "remember my conventions for this repo".
What it loads into context
Frontmatter
234 tokensAlways available to the agent
SKILL.md
3,108 tokensWhen the skill is activated
Reference documents
283 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Absolute Init
- When to use
- Key principles
- Step 1 — DETECT
- Step 2 — RESOLVE existing config
- Step 3 — INTERVIEW
- Step 4 — WRITE
- Config schema
- Precedence (how commands read config)
- Gotchas
- Companion commands
Files
README.mddoc1,107 bytesSKILL.mdcore12,102 bytes
Read SKILL.md
> "set up / initialize / configure absolute").
> Start your first response with the ⚙<U+FE0F> emoji.
## Absolute Init
One-time setup. Detect the project's real conventions, ask a few questions about how you
want absolute to behave, then write that to JSON config the other ten commands read on
every run. Result: commands stop re-detecting your stack from scratch and respect your
preferences (output style, gating, TDD strictness) without being told each time.
This is the only command that writes config. It is non-destructive: an existing config is
shown and updated, never blindly overwritten. It never commits.
---View the complete source on GitHubabsolute-prune
When your agent uses it
Dead code and dependency cleanup, repo-wide: unused deps, unreferenced exports, unreachable code, orphaned files — removed only with tool evidence, in reversible waves. Runs on green main. For diff-scoped cleanup use absolute-simplify. Triggers on "absolute prune", "remove dead code", "find unused deps/exports", "what can we delete", "clean up orphaned files".
What it loads into context
Frontmatter
186 tokensAlways available to the agent
SKILL.md
1,187 tokensWhen the skill is activated
Reference documents
1,468 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Absolute Prune
- When to use
- What it scans
- Risk ranking (TRIAGE)
- Fix & verify
- Gotchas
- Companion commands
Files
README.mddoc728 bytesSKILL.mdcore4,751 bytesreferences/health-engine.mddoc5,408 bytes
Read SKILL.md
> Start your first response with the ✂<U+FE0F> emoji.
## Absolute Prune
Cut dead growth from the repo: unused dependencies, unreferenced exports, unreachable code,
orphaned files. Evidence-based — every removal is backed by a tool that proves nothing
references it — applied in safe waves with tests green after each.
Runs the shared engine in **`references/health-engine.md`** — read it for the
DETECT → SCAN → TRIAGE → FIX → VERIFY → REPORT loop and the safety contract. This file
covers only what's specific to pruning.
---
View the complete source on GitHubabsolute-simplify
When your agent uses it
Use when the user wants to simplify, clean up, refactor, tidy, or refine code — their staged/unstaged git changes or a target file/path. Reduces complexity, flattens nesting, removes redundancy and dead code, scores each change by value (holding low-value churn), then runs tests to prove nothing broke. Invoke on: "simplify", "simplify this", "simplify my code/changes", "clean up", "clean this up", "clean up my changes", "refactor this", "make this cleaner", "tidy this up", "reduce complexity", "flatten this", "remove dead code", "make it more readable", "polish before commit", or "absolute simplify". Acts on your working diff; for repo-wide dead code use absolute-prune; for lint/type debt use absolute-debt.
What it loads into context
Frontmatter
290 tokensAlways available to the agent
SKILL.md
5,972 tokensWhen the skill is activated
Reference documents
14,461 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Absolute Simplify
- When to use this skill
- Hard Gates
- Checklist
- Phase 1: Scope Detection
- Phase 2: Context Gathering
- Phase 3: Language Detection & Reference Loading
- Phase 4: Analysis
- Simplification Value Score
- Phase 5: Apply Simplifications
- Phase 6: Auto-Verify
- Phase 7: Summary
- Key Principles
- Gotchas
- Anti-Patterns and Common Mistakes
- References
- Companion commands
Files
README.mddoc1,079 bytesSKILL.mdcore24,644 bytesSKILL.mdcore24,644 bytesSKILL.mdcore24,644 bytesSKILL.mdcore24,644 bytesSKILL.mdcore24,644 bytesSKILL.mdcore24,644 bytesreferences/css.mddoc4,759 bytesreferences/golang.mddoc9,394 bytesreferences/javascript.mddoc6,322 bytesreferences/python.mddoc8,565 bytesreferences/react.mddoc9,052 bytesreferences/simplification-catalog.mddoc9,252 bytesreferences/sql.mddoc5,033 bytesreferences/tests.mddoc5,617 bytes
Read SKILL.md
> Start your first response with the broom emoji.
## Absolute Simplify
You are an expert code simplification specialist. You act autonomously -- you
detect scope, analyze code, apply simplifications, verify, and report. You do
not ask permission for each change. You prioritize readable, explicit code over
compact solutions. You never change what code does, only how it does it.
---
## When to use this skill
View the complete source on GitHubabsolute-spec
When your agent uses it
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".
What it loads into context
Frontmatter
228 tokensAlways available to the agent
SKILL.md
2,265 tokensWhen the skill is activated
Reference documents
250 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Absolute Spec
- When to use this command
- Key Principles
- The Flow
- Gotchas
- Output / Response Style
- Companion commands
Files
README.mddoc923 bytesSKILL.mdcore9,226 bytesSKILL.mdcore9,226 bytes
Read SKILL.md
> 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.
View the complete source on GitHubabsolute-ui
When your agent uses it
Build polished, intentional UIs with concrete CSS/Tailwind values — typography, color, layout, spacing, dark mode, accessibility, animations, components. Encodes specific, opinionated rules with exact values, not vague advice. Covers buttons, cards, forms, tables, navigation, dashboards, landing pages, onboarding, and more. Triggers on "absolute ui", "design a UI", "style this component", "make this less like AI slop", "fix the spacing/typography/color", "dark mode", "design a pricing page", "make this look better".
What it loads into context
Frontmatter
237 tokensAlways available to the agent
SKILL.md
6,059 tokensWhen the skill is activated
Reference documents
83,908 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Absolute UI
- When to use this skill
- Read config first
- Design thinking
- Key principles
- Core concepts
- Common tasks
- Anti-patterns / common mistakes
- Gotchas
- References
- Pre-delivery checklist
- Companion commands
Files
README.mddoc822 bytesSKILL.mdcore24,259 bytesreferences/accessibility.mddoc8,744 bytesreferences/animation-libraries.mddoc7,172 bytesreferences/atmosphere-and-texture.mddoc11,409 bytesreferences/buttons-and-icons.mddoc10,202 bytesreferences/cards-and-lists.mddoc9,826 bytesreferences/color-and-theming.mddoc17,838 bytesreferences/dashboards.mddoc14,023 bytesreferences/design-tokens.mddoc13,449 bytesreferences/feedback-and-status.mddoc8,102 bytesreferences/forms-and-inputs.mddoc11,739 bytesreferences/grids-spacing-and-layout.mddoc13,394 bytesreferences/images-and-media.mddoc10,360 bytesreferences/landing-pages.mddoc9,725 bytesreferences/micro-animations.mddoc11,171 bytesreferences/microcopy-and-ux-writing.mddoc7,673 bytesreferences/navigation.mddoc10,972 bytesreferences/onboarding.mddoc9,010 bytesreferences/palette-recipes.mddoc6,471 bytesreferences/performance.mddoc8,958 bytesreferences/product-type-guide.mddoc10,991 bytesreferences/responsiveness-and-mobile-nav.mddoc10,228 bytesreferences/scroll-patterns.mddoc8,652 bytesreferences/shadows-and-borders.mddoc10,205 bytesreferences/style-catalog.mddoc16,976 bytesreferences/tables.mddoc7,604 bytesreferences/typography.mddoc15,013 bytesreferences/visual-hierarchy.mddoc8,300 bytes
Read SKILL.md
> Start your first response with the 🧢 emoji.
## Absolute UI
A comprehensive design system knowledge base for building UIs that feel crafted
by a senior designer, not generated by a prompt. This skill encodes specific,
opinionated rules - exact spacing values, proven color ratios, real typography
scales, and battle-tested component patterns. Every recommendation is actionable
with concrete CSS/Tailwind values, not vague advice like "make it clean."
The difference between AI slop and a polished UI comes down to constraint and
restraint - fewer colors used with intention, consistent spacing from a scale,
typography that creates hierarchy without screaming, and micro-interactions that
feel responsive without being distracting.View the complete source on GitHubabsolute-upgrade
When your agent uses it
Dependency upgrades: outdated/vulnerable deps planned into semver waves (patch/minor batched, majors gated and changelog-read), applied incrementally with lockfiles regenerated and tests green after each. Runs on green main. Triggers on "absolute upgrade", "upgrade our dependencies", "bump deps", "update packages", "move off the deprecated X", "clear the Dependabot backlog".
What it loads into context
Frontmatter
183 tokensAlways available to the agent
SKILL.md
1,149 tokensWhen the skill is activated
Reference documents
1,468 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Absolute Upgrade
- When to use
- What it scans
- Risk ranking (TRIAGE)
- Fix & verify
- Gotchas
- Companion commands
Files
README.mddoc731 bytesSKILL.mdcore4,545 bytesreferences/health-engine.mddoc5,408 bytes
Read SKILL.md
> Start your first response with the ⬆<U+FE0F> emoji.
## Absolute Upgrade
Bring dependencies current — safely, in risk-ranked waves, with tests green after each.
Not a blind `npm update`: outdated and vulnerable deps are grouped by blast radius
(patch/minor → safe wave; major/breaking → gated, one at a time, changelog-read), applied
incrementally, and verified against the project's own test suite.
Runs the shared engine in **`references/health-engine.md`** — read it for the
DETECT → SCAN → TRIAGE → FIX → VERIFY → REPORT loop and the safety contract. This file
covers only what's specific to dependency upgrades.
---View the complete source on GitHubabsolute-work
When your agent uses it
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. Handles features, bugs, refactors, greenfield projects, planning breakdowns, and migrations. Triggers on "absolute work", "build this end-to-end", "plan and build", "break this into tasks", "grill me on this plan", "pick up this ticket", "run this migration".
What it loads into context
Frontmatter
215 tokensAlways available to the agent
SKILL.md
5,009 tokensWhen the skill is activated
Reference documents
13,128 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Absolute Work: End-to-End AI Development Lifecycle
- The Phase Gate Rule
- Activation Protocol
- Session Resume Protocol
- Codebase Convention Detection
- When to Use This Skill
- Key Principles
- Phase 1: INTAKE & BRAINSTORM (Relentless Design Interview)
- Phase 2: SPEC (Spec-Driven Development)
- Phase 3: DECOMPOSE & PLAN (Build the Task Board)
- Phase 4: EXECUTE (Onion-Peel, One Safe Wave at a Time)
- Phase 5: VERIFY (Signals + Independent Evaluator)
- Phase 6: CONVERGE (Close Out)
- Gotchas
- Anti-Patterns
- Output / Response Style
- References
- Companion commands
Files
README.mddoc1,176 bytesSKILL.mdcore21,505 bytesSKILL.mdcore21,505 bytesreferences/board-format.mddoc7,643 bytesreferences/execution-model.mddoc8,934 bytesreferences/intake-playbook.mddoc11,244 bytesreferences/migration-playbook.mddoc7,970 bytesreferences/spec-writing.mddoc8,334 bytesreferences/verification-framework.mddoc8,979 bytes
Read SKILL.md
> Start your first response with the 🛠<U+FE0F> emoji.
## Absolute Work: End-to-End AI Development Lifecycle
Absolute Work takes any unit of work — a ticket, a task, a plan, a migration — from
fuzzy intent to verified code. It is one continuous skill with **hard gates** between
phases: brainstorm a shared design, write and review a spec, decompose into a
dependency-graphed task board, then peel tasks off **one safe wave at a time** with
test-first verification. Nothing is assumed, nothing is silently expanded, and no code
is written until the design is approved.
The lifecycle has 6 phases:
**INTAKE & BRAINSTORM → SPEC → DECOMPOSE & PLAN → EXECUTE → VERIFY → CONVERGE**
View the complete source on GitHubSkills included
- absolute-audit
- absolute-debt
- absolute-deflake
- absolute-docs
- absolute-init
- absolute-prune
- absolute-simplify
- absolute-spec
- absolute-ui
- absolute-upgrade
- absolute-work
Repository facts
- License
- MIT
- Created
- Mar 14, 2026
- Last pushed
- Oct 26, 2026
- Forks
- 30
- Open issues
- 0
- Project activity
- Active
Before you install
Instructions onlyAutomated signals, not a guarantee
Checked Nov 5, 2026
Not fully analyzed: some files were too long, unreadable or missing. This never lowers the level.
Show 10 notes
skills/absolute-deflake/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/absolute-docs/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/absolute-docs/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/absolute-simplify/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/absolute-simplify/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/absolute-simplify/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/absolute-simplify/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/absolute-simplify/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/absolute-spec/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/absolute-work/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzed
- No broad tool permissions
- No dangerous shell commands
- 32 network referencesin 16 files: absolute-ui/references/atmosphere-and-texture.md:77 absolute-ui/references/forms-and-inputs.md:84 absolute-docs/references/tutorials.md:77 and 13 more
- 2 obfuscation signalsin 1 file: absolute-docs/references/reference.md:41
- No instruction overrides
- No executable scripts
- 1 reference to secretsin 1 file: absolute-docs/references/style-and-voice.md:76
- No requests to vote in Hot
Show all 35 signals by file
skills/absolute-audit/README.md
- Network accessline 31
- [@dhruvjainin](https://github.com/dhruvjainin)
skills/absolute-debt/README.md
- Network accessline 31
- [@dhruvjainin](https://github.com/dhruvjainin)
skills/absolute-deflake/README.md
- Network accessline 29
- [@dhruvjainin](https://github.com/dhruvjainin)
skills/absolute-docs/README.md
- Network accessline 31
- [@dhruvjainin](https://github.com/dhruvjainin)
skills/absolute-docs/references/reference.md
skills/absolute-docs/references/style-and-voice.md
- Access to secretsline 76
[Credential-related source omitted]
skills/absolute-docs/references/tutorials.md
- Network accessline 77
pre-empt failures that are *likely*, not every imaginable one. 7. **End-state must be self-evidently working.** "The tutorial is done" is not an ending; "open http://localhost:3000 and you'll see your three todos" is. - Network accessline 78
7. **End-state must be self-evidently working.** "The tutorial is done" is not an ending; "open http://localhost:3000 and you'll see your three todos" is. 8. **Keep it small.** A tutorial that takes more than ~30 minutes or builds more - Network accessline 79
ending; "open http://localhost:3000 and you'll see your three todos" is.
skills/absolute-init/README.md
- Network accessline 36
- [@dhruvjainin](https://github.com/dhruvjainin)
skills/absolute-prune/README.md
- Network accessline 31
- [@dhruvjainin](https://github.com/dhruvjainin)
skills/absolute-simplify/README.md
- Network accessline 34
- [@dhruvjainin](https://github.com/dhruvjainin)
skills/absolute-spec/README.md
- Network accessline 37
- [@dhruvjainin](https://github.com/dhruvjainin)
skills/absolute-ui/README.md
- Network accessline 31
- [@dhruvjainin](https://github.com/dhruvjainin)
skills/absolute-ui/references/atmosphere-and-texture.md
- Network accessline 77
position: absolute; inset: 0; filter: url("data:image/svg+xml,%3Csvg xmlns='http://www.w3.org/2000/svg'%3E%3Cfilter id='n'%3E%3CfeTurbulence type='fractalNoise' baseFrequency='0.8' numOctaves='4' stitchTiles='stitch'/%3E%3C/filter%3E%3C - Network accessline 78
inset: 0; filter: url("data:image/svg+xml,%3Csvg xmlns='http://www.w3.org/2000/svg'%3E%3Cfilter id='n'%3E%3CfeTurbulence type='fractalNoise' baseFrequency='0.8' numOctaves='4' stitchTiles='stitch'/%3E%3C/filter%3E%3Crect width='100%25' he - Network accessline 79
filter: url("data:image/svg+xml,%3Csvg xmlns='http://www.w3.org/2000/svg'%3E%3Cfilter id='n'%3E%3CfeTurbulence type='fractalNoise' baseFrequency='0.8' numOctaves='4' stitchTiles='stitch'/%3E%3C/filter%3E%3Crect width='100%25' height='100%25 - Network accessline 92
position: absolute; inset: 0; background: url("data:image/svg+xml,%3Csvg viewBox='0 0 256 256' xmlns='http://www.w3.org/2000/svg'%3E%3Cfilter id='n'%3E%3CfeTurbulence type='fractalNoise' baseFrequency='0.65' numOctaves='3' stitchTiles=' - Network accessline 93
inset: 0; background: url("data:image/svg+xml,%3Csvg viewBox='0 0 256 256' xmlns='http://www.w3.org/2000/svg'%3E%3Cfilter id='n'%3E%3CfeTurbulence type='fractalNoise' baseFrequency='0.65' numOctaves='3' stitchTiles='stitch'/%3E%3C/filter% - Network accessline 94
background: url("data:image/svg+xml,%3Csvg viewBox='0 0 256 256' xmlns='http://www.w3.org/2000/svg'%3E%3Cfilter id='n'%3E%3CfeTurbulence type='fractalNoise' baseFrequency='0.65' numOctaves='3' stitchTiles='stitch'/%3E%3C/filter%3E%3Crect wi - Network accessline 115
position: absolute; inset: 0; background: url("data:image/svg+xml,%3Csvg viewBox='0 0 256 256' xmlns='http://www.w3.org/2000/svg'%3E%3Cfilter id='n'%3E%3CfeTurbulence type='fractalNoise' baseFrequency='0.65' numOctaves='3' stitchTiles=' - Network accessline 116
inset: 0; background: url("data:image/svg+xml,%3Csvg viewBox='0 0 256 256' xmlns='http://www.w3.org/2000/svg'%3E%3Cfilter id='n'%3E%3CfeTurbulence type='fractalNoise' baseFrequency='0.65' numOctaves='3' stitchTiles='stitch'/%3E%3C/filter% - Network accessline 117
background: url("data:image/svg+xml,%3Csvg viewBox='0 0 256 256' xmlns='http://www.w3.org/2000/svg'%3E%3Cfilter id='n'%3E%3CfeTurbulence type='fractalNoise' baseFrequency='0.65' numOctaves='3' stitchTiles='stitch'/%3E%3C/filter%3E%3Crect wi
skills/absolute-ui/references/color-and-theming.md
- Network accessline 378
4. **Skipping contrast checks** - use the browser DevTools accessibility panel or [whocanuse.com](https://whocanuse.com) before shipping. Check all state variants (hover, focus, disabled).
skills/absolute-ui/references/forms-and-inputs.md
- Network accessline 84
width: 16px; height: 16px; background-image: url("data:image/svg+xml,%3Csvg xmlns='http://www.w3.org/2000/svg' viewBox='0 0 16 16' fill='%236b7280'%3E%3Cpath d='M4 6l4 4 4-4'/%3E%3C/svg%3E"); - Network accessline 85
height: 16px; background-image: url("data:image/svg+xml,%3Csvg xmlns='http://www.w3.org/2000/svg' viewBox='0 0 16 16' fill='%236b7280'%3E%3Cpath d='M4 6l4 4 4-4'/%3E%3C/svg%3E"); background-repeat: no-repeat; - Network accessline 86
background-image: url("data:image/svg+xml,%3Csvg xmlns='http://www.w3.org/2000/svg' viewBox='0 0 16 16' fill='%236b7280'%3E%3Cpath d='M4 6l4 4 4-4'/%3E%3C/svg%3E"); - Network accessline 283
.input--success { border-color: #16a34a; background-image: url("data:image/svg+xml,%3Csvg xmlns='http://www.w3.org/2000/svg' viewBox='0 0 16 16' fill='%2316a34a'%3E%3Cpath d='M3 8l3.5 3.5L13 5'/%3E%3C/svg%3E"); - Network accessline 284
border-color: #16a34a; background-image: url("data:image/svg+xml,%3Csvg xmlns='http://www.w3.org/2000/svg' viewBox='0 0 16 16' fill='%2316a34a'%3E%3Cpath d='M3 8l3.5 3.5L13 5'/%3E%3C/svg%3E"); background-repeat: no-repeat; - Network accessline 285
background-image: url("data:image/svg+xml,%3Csvg xmlns='http://www.w3.org/2000/svg' viewBox='0 0 16 16' fill='%2316a34a'%3E%3Cpath d='M3 8l3.5 3.5L13 5'/%3E%3C/svg%3E");
skills/absolute-ui/references/typography.md
- Network accessline 112
/* Pairing 1 - Editorial (Fraunces + Satoshi) */ @import url('https://fonts.googleapis.com/css2?family=Fraunces:opsz,wght@9..144,500;9..144,700&family=Satoshi:wght@400;500&display=swap'); - Network accessline 113
@import url('https://fonts.googleapis.com/css2?family=Fraunces:opsz,wght@9..144,500;9..144,700&family=Satoshi:wght@400;500&display=swap');
skills/absolute-upgrade/README.md
- Network accessline 31
- [@dhruvjainin](https://github.com/dhruvjainin)
skills/absolute-work/README.md
- Network accessline 39
- [@dhruvjainin](https://github.com/dhruvjainin)
How the signals fit together
Facts from a static read of the files at the pinned commit. They describe what the code does, not why.
Some files could not be read; the facts below still hold.
Signal confidence: 35 facts
- Network access in prose of documentationabsolute-audit/README.md:31Low confidence
- Network access in prose of documentationabsolute-debt/README.md:31Low confidence
- Network access in prose of documentationabsolute-deflake/README.md:29Low confidence
- Network access in prose of documentationabsolute-docs/README.md:31Low confidence
- Possible obfuscation in code of documentationabsolute-docs/references/reference.md:41Low confidence
- Possible obfuscation in code of documentationabsolute-docs/references/reference.md:43Low confidence
- Access to secrets in prose of documentation: a variable, placeholder or call, not a stored valueabsolute-docs/references/style-and-voice.md:76Low confidence
- Network access in prose of documentationabsolute-docs/references/tutorials.md:77Low confidence
- Network access in prose of documentationabsolute-docs/references/tutorials.md:78Low confidence
- Network access in prose of documentationabsolute-docs/references/tutorials.md:79Low confidence
- Network access in prose of documentationabsolute-init/README.md:36Low confidence
- Network access in prose of documentationabsolute-prune/README.md:31Low confidence
- Network access in prose of documentationabsolute-simplify/README.md:34Low confidence
- Network access in prose of documentationabsolute-spec/README.md:37Low confidence
- Network access in prose of documentationabsolute-ui/README.md:31Low confidence
- Network access in code of documentationabsolute-ui/references/atmosphere-and-texture.md:77Low confidence
- Network access in code of documentationabsolute-ui/references/atmosphere-and-texture.md:78Low confidence
- Network access in code of documentationabsolute-ui/references/atmosphere-and-texture.md:79Low confidence
- Network access in code of documentationabsolute-ui/references/atmosphere-and-texture.md:92Low confidence
- Network access in code of documentationabsolute-ui/references/atmosphere-and-texture.md:93Low confidence
- Network access in code of documentationabsolute-ui/references/atmosphere-and-texture.md:94Low confidence
- Network access in code of documentationabsolute-ui/references/atmosphere-and-texture.md:115Low confidence
- Network access in code of documentationabsolute-ui/references/atmosphere-and-texture.md:116Low confidence
- Network access in code of documentationabsolute-ui/references/atmosphere-and-texture.md:117Low confidence
- Network access in prose of documentationabsolute-ui/references/color-and-theming.md:378Low confidence
- Network access in code of documentationabsolute-ui/references/forms-and-inputs.md:84Low confidence
- Network access in code of documentationabsolute-ui/references/forms-and-inputs.md:85Low confidence
- Network access in code of documentationabsolute-ui/references/forms-and-inputs.md:86Low confidence
- Network access in code of documentationabsolute-ui/references/forms-and-inputs.md:283Low confidence
- Network access in code of documentationabsolute-ui/references/forms-and-inputs.md:284Low confidence
- Network access in code of documentationabsolute-ui/references/forms-and-inputs.md:285Low confidence
- Network access in code of documentationabsolute-ui/references/typography.md:112Low confidence
- Network access in code of documentationabsolute-ui/references/typography.md:113Low confidence
- Network access in prose of documentationabsolute-upgrade/README.md:31Low confidence
- Network access in prose of documentationabsolute-work/README.md:39Low confidence
Works with
| Agent | Status | Evidence | Install to |
|---|---|---|---|
| Claude Code | Native | Path CLAUDE.md | .claude/skills/<skill-name>/ |
| Codex | Compatible | Standard SKILL.md skills/absolute-audit/SKILL.md | .agents/skills/<skill-name>/ |
| Cursor | Compatible | Standard SKILL.md skills/absolute-audit/SKILL.md | .cursor/skills/<skill-name>/ |
| Gemini CLI | Compatible | Standard SKILL.md skills/absolute-audit/SKILL.md | .gemini/skills/<skill-name>/ |
| GitHub Copilot | Compatible | Standard SKILL.md skills/absolute-audit/SKILL.md | .github/skills/<skill-name>/ |
| OpenCode | Compatible | Standard SKILL.md skills/absolute-audit/SKILL.md | .opencode/skills/<skill-name>/ |
- Native The repository ships a manifest, folder or frontmatter field for this agent.
- Compatible A standard SKILL.md that this agent can read.
- Unknown No evidence either way.
Derived automatically from paths, manifests and frontmatter. Not tested on each agent.