writing-skills
Skill8 starsChanged 4 days agoMITView on GitHub
Use when creating a new skill for this toolkit — ensures the skill follows the anatomy, CSO principle, and is tested against agent rationalizations before shipping.
191 other projects use a version of this.
Adopted by
Most recently taken up by
- AtilaMedeiros/skillstheir own version, first seen Nov 16, 2026
- Floppa2003/skillstheir own version, first seen Nov 16, 2026
- dragoshont/architravetheir own version, first seen Nov 16, 2026
- rundesk-ai/skillstheir own version, first seen Nov 15, 2026
- draekien/skillstheir own version, first seen Nov 15, 2026
- mintunitish/tandemtheir own version, first seen Nov 15, 2026
Used with
Projects with it also use chinese-code-review, chinese-commit-conventions and 10 more.
Other files people use alongside this one.
Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
Leodorareluctant259Skillchinese-code-review
中文代码审查规范——在保持专业严谨的同时,用符合国内团队文化的方式给出有效反馈
Also in 8 projects that use this
Leodorareluctant259Skillchinese-commit-conventions
中文 Git 提交规范 — 适配国内团队的 commit message 规范和 changelog 自动化
Also in 8 projects that use this
obraSkilldiagnosing-superpowers
Use when a superpowers session went wrong and your human partner wants to know why — repeated work, ignored plans, stumbles, poor results, a skill that didn't fire, "it took too long", "why is it so expensive", "what is it doing" — or wants to build a bug report for the superpowers maintainers, for the current session or a past one identified by id or path, on any harness.
Also in 20 projects that use this
kntismSkillcondition-based-waiting
Use when tests have race conditions, timing dependencies, or inconsistent pass/fail behavior - replaces arbitrary timeouts with condition polling to wait for actual state changes, eliminating flaky tests from timing guesses
Also in 3 projects that use this
aaddrickSkillwriting-agents
Use when creating new agents, editing existing agents, or defining specialized subagent roles for the Task tool
Also in 3 projects that use this
pedronauckSkilllesson-learned
Analyze recent code changes via git history and extract software engineering lessons. Use when the user asks 'what is the lesson here?', 'what can I learn from this?', 'engineering takeaway', 'what did I just learn?', 'reflect on this code', or wants to extract principles from recent work.
Also in 3 projects that use this
- +3 more from Leodorareluctant259
Other versions191 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 191
- obra/superpowers★ 314ksame name
- PostHog/posthog★ 41ksame name
- jnMetaCode/superpowers-zh★ 8.5ksame name
- openai/plugins★ 7.8ksame name
- farm-fe/farm★ 5.6ksame name
- compozy/compozy★ 2.9ksame name
- crbnos/carbon★ 2.8ksame name
- lingyired/status-trio★ 2ksame name
- GanyuanRan/Aegis★ 1.4ksame name
- pcvelz/superpowers★ 1.3ksame name
181 more not listed
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository34 other files it gives its agents.
- AGENTS.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- batch-fixSkill
- brainstormingSkill
- code-review-and-qualitySkill
- code-simplificationSkill
- context-engineeringSkill
- fixSkill
- handoffSkill
- implementSkill
- incremental-implementationSkill
- instructionsSkill
- lessonsSkill
- mtk-doctorSkill
- mtk-setupSkill
- mtkSkill
- planning-and-task-breakdownSkill
- pre-commit-reviewSkill
- prior-work-checkSkill
- promote-lessonSkill
- repo-healthSkill
- research-contextSkill
- security-and-hardeningSkill
- setup-auditSkill
- setup-bootstrapSkill
- setup-refreshSkill
- spec-drift-detectionSkill
- spec-driven-developmentSkill
- subagent-implementationSkill
- tech-stack-dotnetSkill
- tech-stack-pythonSkill
- tech-stack-typescriptSkill
- verification-before-completionSkill
- workflow-artifactsSkill
The file
Show its rules and text
We split this skill into the rules it gives an agent
23 rules. 0 are common, 17 are distinctive, and 6 are very specific to this project.
0
Common
Most of the 181 edited versions we read keep these.
17
Distinctive
This author's own choices. Worth a look.
6
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 31
Before writing any skill content:
- Distinctive: line 33
Run 2-3 representative scenarios without the skill.
- Distinctive: line 34
Document what went wrong:
- Very specific: line 42
Follow the anatomy defined in docs/skill-anatomy.md:
- Distinctive: line 45
Do not add rationalization tables, red-flag lists, or ALL-CAPS emphasis.
- Distinctive: line 52
Put field-earned rules in the workflow: When a baseline failure shows a step being skipped, close it with one plain sentence in that step …
- Distinctive: line 54
Write verification checklist: Every claim the skill makes about outcomes must have a verification step.
- Distinctive: line 56
Keep it under 500 lines: If the skill needs more, use progressive disclosure:
- Distinctive: line 65
Create 3-5 adversarial scenarios that try to break the skill's discipline:
- Distinctive: line 71
Run each scenario and verify the skill holds.
- Distinctive: line 72
If the skill breaks, strengthen the specific gap:
- Distinctive: line 79
If the skill is on the ship path — meaning a miss ends up in a commit, a PR, or a release — add measurable evals in addition to pressure …
- Very specific: line 82
Add a native claude plugin eval case: evals/<case>/prompt.md (the user prompt plus tags, limits and allowed_tools frontmatter), case.yaml …
- Very specific: line 86
Prefer deterministic graders (regex over a produced file or the trace, tool_used, file_exists) and keep llm rubrics to short outputs with …
- Very specific: line 101
Add the skill to .claude/manifest.json with action sync.
- Distinctive: line 102
Add routing rules to AGENTS.md if the skill changes how tasks are dispatched.
- Very specific: line 103
Update docs/skill-anatomy.md if the skill establishes a new pattern.
- Very specific: line 104
Run bash scripts/validate-toolkit.sh to verify the skill passes validation.
- Distinctive: line 112
Rule: put invariants first, volatile state last.
- Distinctive: line 123
No skill without baseline failure observations.
- Distinctive: line 125
No skill without a verification checklist.
- Distinctive: line 127
Keep frequently-loaded skills under 500 lines.
- Distinctive: line 128
Test discipline-enforcing skills with adversarial pressure scenarios.
“Common” is measured: kept by at least 6 in 10 of the 181 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Writing Skills
Overview
A skill is a reusable behavior contract that shapes how an agent approaches a category of work. Writing a good skill requires observing baseline failures first, then writing the minimum documentation that closes those gaps, then testing that the skill resists pressure.
When To Use
- Adding a new skill to the toolkit
- Substantially rewriting an existing skill
When NOT To Use
- One-off project-specific conventions (put those in CLAUDE.md)
- Mechanical constraints better handled by automation (put those in hooks or settings)
Workflow
Phase 1: Observe Baseline Failures
Before writing any skill content:
- Run 2-3 representative scenarios without the skill.
- Document what went wrong:
- What steps were skipped?
- What rationalizations were used to skip them?
- What outcomes were produced?
- This creates the "RED" baseline — the specific gaps the skill must close.
Phase 2: Write The Minimum Skill
- Follow the anatomy defined in
docs/skill-anatomy.md:- Required: frontmatter (
name,description,type: skill— ortype: tech-stackfor tech stack skills),# Title,## Overview,## When To Use,## Workflow,## Verification - Recommended:
### When NOT To Use,## Rules - Do not add rationalization tables, red-flag lists, or ALL-CAPS emphasis. Current models follow instructions literally and over-trigger on pressure language; state each rule once, in plain words, in the step it governs.
- Required: frontmatter (
- Apply the CSO principle: The
descriptionin frontmatter must trigger on conditions, not summarize the workflow.- Bad: "Create implementation plans with acceptance criteria and dependency ordering"
- Good: "Use after a spec is approved and before multi-file implementation begins"
- Why: Workflow summaries cause the agent to follow the description instead of reading the full SKILL.md
- Put field-earned rules in the workflow: When a baseline failure shows a step being skipped, close it with one plain sentence in that step (what to do and, if it is not obvious, why). Do not restate it in a separate table or list.
- Write verification checklist: Every claim the skill makes about outcomes must have a verification step.
- Keep it under 500 lines. If the skill needs more, use progressive disclosure:
- Core workflow in SKILL.md
- Reference material in separate files loaded on demand
- The SKILL.md is a navigation layer, not a payload (S2.26): it holds the decision logic and links to references — it does not inline detail it could point to. The budget is the ceiling, not the target.
Phase 3: Test Under Pressure
- Create 3-5 adversarial scenarios that try to break the skill's discipline:
- Time pressure: "We need to ship this now, skip X"
- Simplicity argument: "This is too simple to need X"
- Authority argument: "The engineer said to skip X"
- Precedent argument: "We didn't do X last time and it was fine"
- Run each scenario and verify the skill holds.
- If the skill breaks, strengthen the specific gap:
- Tighten the workflow step that was skipped
- Save pressure tests to
tests/pressure-tests/<skill-name>-pressure.md.
Phase 3b: Add Evals (If The Skill Gates Shipping)
If the skill is on the ship path — meaning a miss ends up in a commit, a PR, or a release — add measurable evals in addition to pressure tests:
- Add a native
claude plugin evalcase:evals/<case>/prompt.md(the user prompt plustags, limits andallowed_toolsfrontmatter),case.yamlnaming ascaffold.shthat builds the repo the prompt runs in, and one grader per file undergraders/. Layout and run commands:evals/README.md. - Prefer deterministic graders (
regexover a produced file or the trace,tool_used,file_exists) and keepllmrubrics to short outputs with concrete PASS/FAIL conditions. Grade behaviour, not wording. - Mark graders that can only pass with the plugin
arm: with-only, and "must not do X" checksarm: both, so the without-plugin arm stays comparable. - Tag the case
core(andsmokeif it is cheap), then iterate withclaude plugin eval . --case <case> --runs 1 --ablation none --scaffold --allow-tools Bash Write Edit --trust-pluginuntil it loads and grades sensibly.
Pressure tests are adversarial-only scenarios read by a human. Evals are executed and give a measurable score against a no-plugin baseline. Use both for ship-path skills; pressure tests alone are sufficient for advisory skills.
Phase 4: Register
- Add the skill to
.claude/manifest.jsonwith actionsync. - Add routing rules to
AGENTS.mdif the skill changes how tasks are dispatched. - Update
docs/skill-anatomy.mdif the skill establishes a new pattern. - Run
bash scripts/validate-toolkit.shto verify the skill passes validation.
Note: tech stack skills (type: tech-stack) follow the S2.13 declarative anatomy instead of the workflow anatomy above.
Cache-Stable Prefixes
When a skill runs repeatedly across sessions — especially a reviewer agent or an entry-point skill that the whole team loads on every run — prompt caching cuts token cost dramatically. Caching works by matching an exact prefix of the prompt. If the prefix changes every session (because a date, branch, or diff stat is at the top), the cache misses.
Rule: put invariants first, volatile state last.
- Invariants (top): persona statement, output contract, standards checklist. These never change between sessions.
- Dynamic state (bottom): current branch, diff stats, touched files, behavioral diff. Inject these via
!`command`fenced blocks or at the call site, not woven through the static body.
A good reviewer agent has the same top ~80% byte-for-byte across every invocation, with only the diff + behavioral-diff injected at the end. That prefix caches; subsequent sessions pay only for the tail.
Entry-point skills follow the same pattern — Phase 0 load instructions stay identical, only the user-supplied task description varies.
Rules
- No skill without baseline failure observations.
- Field-earned rules live in the workflow step they govern, stated once in plain words.
- No skill without a verification checklist.
- Descriptions trigger on conditions, never summarize workflows (CSO principle).
- Keep frequently-loaded skills under 500 lines.
- Test discipline-enforcing skills with adversarial pressure scenarios.
- Cache-stable prefix for reviewer agents and high-traffic entry-point skills: invariants top, dynamic state bottom.
Verification
- Baseline failures were documented before writing the skill
- Description follows the CSO principle (condition-based triggering)
- Every skippable step states its rule in the step itself (no rationalization tables or red-flag lists)
- Verification checklist covers every outcome claim
- SKILL.md is under 500 lines
- Pressure tests exist and the skill passes them
- If this skill claims another skill consumes/invokes/checks its output, grep that skill and confirm the reciprocal reference exists
- Skill is registered in manifest.json and
validate-toolkit.shpasses
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

