sync-changelog

Use after a release succeeds, when maintainers need to sync apps/kimi-code/CHANGELOG.md into docs/en/release-notes/changelog.md and docs/zh/release-notes/changelog.md, then open a PR on a dedicated branch.

Quality

88%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Quality

Content

77%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The body is a highly actionable, well-sequenced multi-step workflow with strong validation checkpoints and a clear review feedback loop. Its main weakness is conciseness and progressive disclosure: the long single-file body repeats guidance across Workflow, Rules, and Common Mistakes, and keeps substantial reference-style detail inline rather than splitting it into one-level-deep reference files.

Suggestions

Consolidate the overlapping guidance: the Rules section and the Common Mistakes table largely restate Preconditions and workflow steps — either fold the unique rules into the relevant steps or move Common Mistakes to a separate reference file to trim ~25 redundant rows.

Split the heavy inline reference material (the classification keyword-hint lists and the Chinese wording-style guide) into a bundled reference file (e.g. references/classification.md) linked from the workflow, so the SKILL.md body stays a lean overview with one-level-deep navigation.

Tighten step 3 and step 4: the stripping rules and merge/dedup rules each repeat the same 'drop SDK-only / provider-internal detail' instruction in multiple places — state it once and reference it.

Dimension	Reasoning	Score
Conciseness	The core workflow is dense procedural knowledge Claude would not know (changesets format, five section types, merge/dedup rules), but the ~470-line body carries notable redundancy — the Rules section restates Preconditions and the large Common Mistakes table rephrases guidance already in the workflow steps — fitting 'mostly efficient but ... could be tightened' rather than the lean score-3 anchor.	2 / 3
Actionability	Provides fully executable, copy-paste-ready commands (git fetch/checkout -b, rg, git log --format=%cs, gh pr view/create, pnpm --filter docs run build) plus exact markdown formats, a complete example PR body, and a worked before/after translation example, matching 'Fully executable code/commands; copy-paste ready'.	3 / 3
Workflow Clarity	A clearly sequenced 10-step workflow with explicit validation (step 7 verify checks + docs build), a Stop Signals section, and a human-review feedback loop ('re-run verification from step 7 and return to this checkpoint'), matching 'Clear sequence with explicit validation steps; feedback loops for error recovery'.	3 / 3
Progressive Disclosure	Sections are well-organized and it appropriately delegates to external materials (translate-docs, gen-changesets, docs/AGENTS.md) instead of re-explaining them, but no bundle reference files exist and the large inline detail (Common Mistakes table, keyword-hint lists, Chinese wording style) is content that could be split out for a skill this complex, fitting 'Some structure but ... content that should be separate is inline' rather than the one-level-deep score-3 anchor.	2 / 3
	Total	10 / 12 Passed

Description

100%

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

The description is concise, specific, and uses natural third-person trigger phrasing that names exact source/target paths and the post-release PR workflow. It cleanly answers both what the skill does and when to invoke it, with a distinct niche unlikely to collide with other skills.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — 'sync apps/kimi-code/CHANGELOG.md into docs/en/... and docs/zh/...changelog.md, then open a PR on a dedicated branch' — with exact file paths and a specific outcome, matching the 'Lists multiple specific concrete actions' anchor rather than the score-2 'Names domain and some actions'.	3 / 3
Completeness	Explicitly answers both 'what' (sync the CLI changelog into the two docs pages and open a PR) and 'when' ('Use after a release succeeds, when maintainers need to sync...'), satisfying the 'Clearly answers both what AND when with explicit triggers' anchor rather than score 2 where 'when' is only implied.	3 / 3
Trigger Term Quality	Natural trigger phrasing a maintainer would say — 'after a release succeeds', 'sync ... changelog', 'open a PR on a dedicated branch' — gives good coverage of real-world terms; not jargon-only (score 1) nor merely partial (score 2).	3 / 3
Distinctiveness Conflict Risk	A precise niche — syncing one specific changelog into two specific docs files post-release — with triggers unlikely to fire for other skills, matching 'Clear niche with distinct triggers; unlikely to conflict'; it is more specific than the score-2 'Works with document files'.	3 / 3
	Total	12 / 12 Passed

Validation

93%

Warnings & errors only

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
relative_links	Relative link issues: 5 suspicious	Warning

	Total	15 / 16 Passed

Repository: MoonshotAI/kimi-code
Path: .agents/skills/sync-changelog/SKILL.md
Commit: 77618e3

Reviewed: 2 days ago

Table of Contents

Discovery Implementation Validation

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.