writing-plans
Skill1 starsChanged 9 months agoNo licenceView on GitHub
Use when you have a spec or requirements for a multi-step task, before touching code
198 other projects use a version of this, 128 of them edited; 100 of 119 edited versions we compared changed its rules; 11 new projects in the last 4 weeks, against 14 the 4 before.
How people change it
100 of 119 edited versions changed its rules, and some changes recur.
Of the 119 edited versions we compared: 19 keep every rule, 100 made changes of their own.
Rules people drop
- After saving the plan, offer execution choice:dropped by 42 of 100
- REQUIRED SUB-SKILL: Use superpowers:subagent-driven-developmentdropped by 31 of 100
Rules people add
- Before defining tasks, map out which files will be created or modified and what each one is responsible for. This is where decomposition decisions get locked in.added by 73 of 100
- If the spec covers multiple independent subsystems, it should have been broken into sub-project specs during brainstorming. If it wasn't, suggest breaking this into separate plans — one per subsystem. …added by 72 of 100
- 3. Type consistency: Do the types, method signatures, and property names you used in later tasks match what you defined in earlier tasks? A function called
clearLayers()in Task 3 butclearFullLayers()in Task 7 is a bug.added by 64 of 100 - After writing the complete plan, look at the spec with fresh eyes and check the plan against it. This is a checklist you run yourself — not a subagent dispatch.added by 63 of 100
- If you find issues, fix them inline. No need to re-review — just fix and move on. If you find a spec requirement with no task, add the task.added by 62 of 100
- Context: If working in an isolated worktree, it should have been created via the
superpowers:using-git-worktreesskill at execution time.added by 51 of 100 - A rule we can't quote: its licence doesn't allow itadded by 46 of 100
- A rule we can't quote: its licence doesn't allow itadded by 43 of 100
We split this file and each edited version into the rules they give an agent and match them by wording. A version that adds no rule of its own and has not changed since this file last did reads as an older text, so what it lacks is not counted as dropped. We keep no past texts of a file, so that is inferred, and an edited version that started from an older text still counts its gaps as drops.
Adopted by
Cooling: 11 new projects took it in the last 4 weeks, 0.8× the 4 weeks before.
Most recently taken up by
- Badhon-00/MDCPedited, first seen Nov 16, 2026
- b-mendoza/agent-skillsedited, first seen Nov 16, 2026
- wxxb789/hoaedited, first seen Nov 16, 2026
- mintunitish/tandemedited, first seen Nov 15, 2026
- FimawLLC/fimaw-skillsedited, first seen Nov 15, 2026
- mdiri-ai/SoduWorkedited, 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
ryanportfolioSkilladdskill
Create, import, update, or install repo or personal skills: runtime ownership, resources, discovery checks.
Also in 6 projects that use this
ryanportfolioSkillapply-firmware
Bring current folder (plain folder, existing repo, old or partial firmware copy) up to full Harness Firmware in place. Mirror external repo → adopt-repo.
Also in 6 projects that use this
- +2 more from Leodorareluctant259
- +6 more from ryanportfolio
Other versions198 projects use a version of this.
Word for word · 24
- DemonDamon/AgenticX★ 1k100% same
- ARounder-183/HiFiShifter★ 93100% same
- cooker/wxHm★ 70100% same
- myths-labs/muse★ 38100% same
- abudhahir/superpowers★ 18100% same
- choupiyang/ZAI_SKILLS★ 13100% same
- xfstudio/skills★ 9100% same
- 4gentic/obelus★ 8100% same
- dazeb/ClaudePlaybook★ 8100% same
- jordanhindo/Turtlez★ 4100% same
- Cygnusfear/claude-stuff★ 4100% same
13 more not listed
Edited · 128
- obra/superpowers★ 314k13% same
- openai/plugins★ 7.8k33% same
- farm-fe/farm★ 5.6k39% same
- microsoft/FluidFramework★ 4.9k17% same
- lingyired/status-trio★ 1.8k13% same
- revokslab/ShipFree★ 1.7k100% same
- math-inc/OpenGauss★ 1.3k16% same
- mdiri-ai/SoduWork★ 93032% same
- coco-research/coco★ 79745% same
- AgentTeam-TaichuAI/ScienceClaw★ 67146% same
118 more not listed
Wrote their own version · 46
- jnMetaCode/superpowers-zh★ 8.5ksame name
- GanyuanRan/Aegis★ 1.4ksame name
- pcvelz/superpowers★ 1.3ksame name
- kid-sid/claude-spellbook★ 190same name
- REPOZY/superpowers-optimized★ 146same name
- withzombies/hyperpowers★ 80same name
- AlekseiUL/sprut-agent-kit★ 66same name
- joshuadavidthomas/agent-skills★ 49same name
- johnqtcg/awesome-skills★ 30same name
- megamott/vibe-skills★ 28same name
36 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 repository704 other files it gives its agents.
- postgres-best-practices/AGENTS.mdAGENTS.md
- react-best-practices/AGENTS.mdAGENTS.md
- loki-mode/CLAUDE.mdCLAUDE.md
- 3d-web-experienceSkill
- ab-test-setupSkill
- accessibility-compliance-accessibility-auditSkill
- activecampaign-automationSkill
- Active Directory AttacksSkill
- address-github-commentsSkill
- agent-evaluationSkill
- agent-manager-skillSkill
- agent-memory-mcpSkill
- agent-memory-systemsSkill
- agent-orchestration-improve-agentSkill
- agent-orchestration-multi-agent-optimizeSkill
- agent-tool-builderSkill
- ai-agents-architectSkill
- ai-engineerSkill
- ai-productSkill
- airflow-dag-patternsSkill
- airtable-automationSkill
- ai-wrapper-productSkill
- algolia-searchSkill
- algorithmic-artSkill
- amplitude-automationSkill
- analytics-trackingSkill
- angular-best-practicesSkill
- angular-migrationSkill
- angularSkill
- angular-state-managementSkill
- angular-ui-patternsSkill
- anti-reversing-techniquesSkill
- api-design-principlesSkill
- api-documentation-generatorSkill
- api-documenterSkill
- API Fuzzing for Bug BountySkill
- api-patternsSkill
- api-security-best-practicesSkill
- api-testing-observability-api-mockSkill
- app-builderSkill
- application-performance-performance-optimizationSkill
- app-store-optimizationSkill
- architect-reviewSkill
- architecture-decision-recordsSkill
- architecture-patternsSkill
- architectureSkill
- arm-cortex-expertSkill
- asana-automationSkill
- async-python-patternsSkill
- attack-tree-constructionSkill
- audio-transcriberSkill
- auth-implementation-patternsSkill
- automate-whatsappSkill
- autonomous-agent-patternsSkill
- autonomous-agentsSkill
- avalonia-layout-zafiroSkill
- avalonia-viewmodels-zafiroSkill
- avalonia-zafiro-developmentSkill
- AWS Penetration TestingSkill
- aws-serverlessSkill
- The first 60 shown.
The file
We split this skill into the rules it gives an agent
2 rules. 0 are common, 2 are distinctive, and 0 are very specific to this project.
0
Common
Most of the 156 edited versions we read keep these.
2
Distinctive
This author's own choices. Worth a look.
0
Very specific
Tied to their project's names, files or tools. Probably skip.
No licence file, so all rights are reserved — read it at the source. We count its rules but don't quote them. Read them on GitHub.
“Common” is measured: kept by at least 6 in 10 of the 156 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.
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.

