feature
Skill17 starsChanged 14 days agoMITView on GitHub
Develop requirements, dependencies and an implementation approach for new or deliberately changed behavior. Use for /haechi:feature or when those methods help an authorized product change.
71 other projects use a version of this.
Adopted by
Most recently taken up by
- 5hirish/ducttheir own version, first seen Nov 8, 2026
- paulocsb/worldcup-fifa-pooltheir own version, first seen Nov 8, 2026
- vocion/vocion-coretheir own version, first seen Nov 8, 2026
- yicheng47/runnertheir own version, first seen Nov 7, 2026
- crbnos/carbontheir own version, first seen Nov 7, 2026
- hex/claude-sessionstheir own version, first seen Nov 3, 2026
Used with
Projects with it also use bugfix, adopt and 8 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.
team-attentionSkillbugfix
Root cause based one-shot bug fix. debugger diagnosis → requirements.md generation → /execute. /bugfix "error description" Full investigation pipeline: debugger + gap-analyzer + standard verify. QA suggestion after successful fix.
Also in 7 projects that use this
codebycoreySkilladopt
Adopt an existing plan from conversation context into delta-spec format. Use when importing a plan, adopting planning that already happened, capturing plan mode output, or bringing in prior design work.
Also in 4 projects that use this
Google CloudSkillfix
Plan a remediation strategy after a test failure.
Also in 10 projects that use this
marylinSkillrecover
Recover work from a crashed or interrupted session. Use when Claude crashed mid-task, after an unexpected exit, when you see 'stale sessions detected', or when you lost context and need to figure out what was happening.
Also in 3 projects that use this
AWSSkillmap
Map verified service capabilities against customer-provided control framework and threat model. Produces mapping-results.json, controls-catalog.md, and framework-mapping.md. Supports pluggable frameworks: CCMv4, NIST 800-53, CIS Benchmarks, ISO 27001, etc. Split into 4 focused sub-skills for better accuracy; this skill orchestrates them.
Also in 4 projects that use this
corygabrielsenSkillspike
Implement N approaches as separate branches, then compare side-by-side. Removes "implementation effort" as a variable from the decision.
Also in 4 projects that use this
Other versions71 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 71
- crbnos/carbon★ 2.8ksame name
- aaronjmars/aeon★ 789same name
- aeonfun/aeon★ 789same name
- astashov/liftosaur★ 775same name
- me2resh/apexyard★ 542same name
- yicheng47/runner★ 490same name
- bradtraversy/coding-with-ai-course-resources★ 344same name
- garagon/nanostack★ 206same name
- DeL-TaiseiOzaki/claude-code-orchestra★ 199same name
- vide/matedroid★ 86same name
61 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 repository32 other files it gives its agents.
- AGENTS.mdAGENTS.md
- aboutSkill
- answerSkill
- attack-testsSkill
- audit-experimentSkill
- bugSkill
- ci-watchSkill
- commitSkill
- contextSkill
- delegateSkill
- documentSkill
- evalSkill
- impact-mapSkill
- implement-workSkill
- mrSkill
- mutation-checkSkill
- perfSkill
- previewSkill
- refactorSkill
- requestSkill
- review-diffSkill
- reviewSkill
- run-experimentSkill
- screen-designSkill
- screen-paritySkill
- setupSkill
- sibling-path-mapSkill
- specSkill
- sweepSkill
- test-hardeningSkill
- verify-workSkill
- work-graphSkill
The file
We split this skill into the rules it gives an agent
2 rules. 0 are common, 1 is distinctive, and 1 is very specific to this project.
0
Common
Most of the 65 edited versions we read keep these.
1
Distinctive
This author's own choices. Worth a look.
1
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 14
Check external contracts: Verify that the backend/API/dependency supports required fields, parameters and states.
- Distinctive: line 18
Use the common contract's Check section and relevant review/screen methods to decide completion.
“Common” is measured: kept by at least 6 in 10 of the 65 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
Develop a change
Apply the common work contract within the authorized scope. It owns required implementation, verification, review and completion obligations; this skill supplies methods. Use /haechi:delegate for a bounded worker task when independent execution helps. Existing step names below are compatible delegation entry points, not an exclusive workflow state.
Methods
- Establish the intended behavior. Identify who uses it, the trigger, expected result, relevant exceptions and behavior to preserve. Reuse accepted requirements. Use /haechi:spec when synthesis of interacting requirements helps; an existing sufficiently complete account needs no new document or approval.
- Establish the design reference. For visible UI or interaction changes, use an accepted and checked reference that covers the need. Use /haechi:preview for missing states or design choices before dependent implementation. Retain the selected reference and checked interactions for the real application comparison.
- Check external contracts. Verify that the backend/API/dependency supports required fields, parameters and states. Use the installed version's source or authoritative documentation. Identify missing support and resolve any consequential change of scope before relying on a workaround.
- Choose units and interfaces. Inspect entry points, existing components, tokens, consumers and tests. Prefer reuse or a compatible extension when it fits. Settle shared interfaces before dependent work; separate file ownership when delegation helps. A file count alone does not justify parallel work.
- Implement the authorized change. Work directly or assign bounded implementation through /haechi:delegate. Use another task method when a finding changes the next action; do not restart completed requirements or design work merely to enter that method.
Use the common contract's Check section and relevant review/screen methods to decide completion. New behavior and preservation evidence must both cover the final relevant change.
Delegation contracts
These compatible entries identify delegated methods, not an exclusive workflow or a mandatory agent sequence. Packet assembly also supplies the canonical common work contract. The main session fills the named context fields and task-specific acceptance criteria; detailed procedures and principle bodies stay in their referenced files. read-only means repository files remain unchanged; authorized temporary or report outputs must be named separately in artifactPaths.
{
"implement": {
"skills": [
"implement-work"
],
"principles": [
"dry",
"yagni",
"kiss",
"boundary-validation",
"root-cause",
"failing-test-first",
"behavior-tests"
],
"checks": [],
"writeScope": "scoped",
"contextRequired": [
"repository",
"requirements",
"acceptanceChecks",
"ownership"
],
"completion": [
"Report the assigned implement work, its observed results and any remaining scope limitations."
]
},
"attack": {
"skills": [
"attack-tests",
"sibling-path-map",
"mutation-check"
],
"principles": [
"sibling-paths",
"behavior-tests"
],
"checks": [],
"writeScope": "scoped",
"contextRequired": [
"repository",
"requirements",
"changedFiles",
"ownership"
],
"completion": [
"Demonstrate that tests detect the targeted defects without weakening expected behavior."
]
},
"review": {
"skills": [
"verify-work",
"review-diff",
"impact-map"
],
"principles": [
"evidence-levels",
"behavior-tests"
],
"checks": [
"agent-defects",
"sibling-paths",
"dry",
"yagni",
"kiss"
],
"writeScope": "read-only",
"contextRequired": [
"repository",
"requirements",
"base",
"changedFiles",
"priorEvidence"
],
"completion": [
"Report concrete defects with expected and observed behavior and affected consumers.",
"Distinguish passing checks, failures, missing proof and unresolved expectations."
]
},
"design": {
"skills": [
"screen-design"
],
"principles": [
"real-artifact"
],
"checks": [],
"writeScope": "read-only",
"contextRequired": [
"repository",
"designSource",
"urls",
"states",
"artifactLocation",
"loginContext"
],
"completion": [
"For a supplied design, return MATCH or MISMATCH with actual rendered comparisons, or BLOCKED with missing evidence."
]
},
"parity": {
"skills": [
"screen-parity"
],
"principles": [
"real-artifact"
],
"checks": [],
"writeScope": "read-only",
"contextRequired": [
"repository",
"beforeUrl",
"afterUrl",
"states",
"intendedDifferences",
"artifactLocation",
"loginContext"
],
"completion": [
"Return PASS or FAIL against real rendered comparisons and the noise baseline, or BLOCKED."
]
}
}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.

