feature-changelog
Skill0 starsChanged 4 months agoMITView on GitHub
Maintain FEATURE_CHANGELOG.md - the functional feature registry. Baseline discovery, duplicate/extension detection before planning, deterministic feature IDs, post-approval updates, and index validation.
In this repository8 other files it gives its agents.
- codex-reviewSkill
- deploymentSkill
- frappe-taskSkill
- git-finalizationSkill
- project-contextSkill
- task-implementationSkill
- task-planningSkill
- testing-taskSkill
The file
We split this skill into the rules it gives an agent
3 rules. About 0 are common, 1 is distinctive, and 2 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈1
Distinctive · estimate
This author's own choices. Worth a look.
2
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 20
Before any docs/ai-context/TASK_PLAN.md is created or accepted → feature search (references/feature-detection.md).
- Very specific: line 24
After a valid Codex APPROVED, during finalization → registry update.
- Distinctive: line 38
Search verdicts for planning: already implemented / related (extension) / new — always confirmed by inspecting actual files, never by text …
≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Feature Changelog Skill
Owns docs/ai-context/FEATURE_CHANGELOG.md: a registry of product
behavior used to decide
whether requested work already exists, extends something, or is new. It
records meaningful business logic only — never commits, renames,
formatting, or refactors without behavior change. The whole file is English.
When to Use
initwith nodocs/ai-context/FEATURE_CHANGELOG.md→ baseline discovery (references/baseline-analysis.md).- Before any
docs/ai-context/TASK_PLAN.mdis created or accepted → feature search (references/feature-detection.md). - New IDs → references/feature-id-rules.md.
- After a valid Codex
APPROVED, during finalization → registry update. - Any registry edit → references/index-validation.md.
Inputs
docs/ai-context/FEATURE_CHANGELOG.md(or its absence), the task description/plan,docs/ai-context/PROJECT_CONTEXT.md, the repository itself.- Deterministic helpers:
bin/frappe-workflow feature search <query>,feature next-id --type <type> --module <module>,feature validate-index.
Outputs
- Search verdicts for planning: already implemented / related (extension) / new — always confirmed by inspecting actual files, never by text similarity alone.
- Registry entries following the template format in
templates/project/FEATURE_CHANGELOG.mdin the plugin (Index row + detailed entry grouped by module).
Preconditions
- Registry updates (beyond baseline) happen only in finalization —
after implementation complete, validations and tests passed, and a valid
APPROVEDwith matching fingerprint.
Stopping Conditions
bin/frappe-workflow feature validate-indexpasses after every edit.- Baseline: all High-confidence entries written; Medium noted; Low listed for user confirmation — then stop.
Prohibited
- Updating the registry during implementation or review rounds.
- Calculating IDs by guessing — only
feature next-idoutput. - Changing an existing ID, ever (renames keep the ID).
- Statuses other than
Active,Deprecated,Replaced,Removed. - Inventing feature history or dates (unknown dates stay
Unknown).
Update Rules at Finalization
- New capability → new entry (Index row + detail, next deterministic ID).
- Extension → same ID: update
Last Updated, Behavior/Main Files when needed, add a Change History dated entry. - Bugfix of an existing feature → Change History entry on that feature;
an independent
BUG-entry only when important, independent, and not clearly owned by an existing feature. - Replacement → old entry
Status: Replaced+Replaced By:; new entry may carryReplaces:.
Shared Rules
shared-workflow-rules.md, file-lifecycle.md.
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.

