diff-skill
Compare two versions of a skill's instructions to detect degradations and complexity increases. TRIGGER when: user asks to diff, compare, or review changes to a skill's markdown instructions. Asymmetric check — only regressions count. Additions, clarifications, and strengthenings
Install
npx skills add https://github.com/serpro69/claude-toolbox/tree/master/klaude-plugin/skills/diff-skill
claude plugin marketplace add https://llmmart.ai/marketplace.json && claude plugin install serpro69-claude-toolbox@llmmart
git clone https://github.com/serpro69/claude-toolbox.git
The skills CLI installs just this skill, for any of its supported agents. Claude Code installs the whole serpro69/claude-toolbox collection as a plugin from our marketplace. Git is the plain clone.
Skill manifest
Diff Skill Instructions
Goal: Detect whether an edit to a skill's markdown instructions introduced degradations or made the skill harder for an LLM to follow.
Two judgment axes:
- Degradation (asymmetric) — load-bearing instruction dropped, constraint weakened, verification step removed, scope narrowed, required output dropped, or reference broken. Content relocated but preserved is neutral.
- Complexity — split into regressions (introduced or worsened by the edit, affects verdict) and pre-existing advisories (exist regardless of the edit, surfaced as improvement opportunities, does NOT affect verdict).
Conventions
- Read capy knowledge base conventions at shared-capy-knowledge-protocol.md.
Required Outputs
- Report written to
docs/reviews/diff-skill/<slug>-<sha-a>-<sha-b>.md - Inline summary presented (under 10 lines: verdict, finding counts, report path)
- Capy indexed under
kk:review-findingsif any degradation or complexity regression findings exist (skip on clean results and pre-existing advisories)
Invocation
/kk:diff-skill <skill-name>
Convenience shortcut: resolves klaude-plugin/skills/<skill-name>/SKILL.md. If not found, asks the user for the skill directory path.
Defaults: HEAD (before) → working tree (after). User can specify different refs in the prompt.
Workflow
Mandatory order — load instructions before acting on subject matter. The phases below are strictly sequential. Do not read skill content, build file sets, or produce judgments until you have loaded and internalized the full process file. The only early contact with the target skill is its name and SKILL.md path — enough to validate, not enough to judge.
See diff-process.md for the detailed step-by-step process.
Files (claude-toolbox)
-
evals
-
clean-refactor
-
test-files
-
after
-
review-process.md 758 B
Loading… -
SKILL.md 656 B
Loading…
-
-
before
-
SKILL.md 1 KB
Loading…
-
-
-
eval.json 1.5 KB
Loading…
-
-
known-degradation
-
test-files
-
after
-
example-process.md 555 B
Loading… -
shared-conventions.md 160 B
Loading… -
SKILL.md 675 B
Loading…
-
-
before
-
example-process.md 553 B
Loading… -
shared-conventions.md 109 B
Loading… -
SKILL.md 725 B
Loading…
-
-
-
eval.json 1.9 KB
Loading…
-
-
-
diff-process.md 8.3 KB
Loading… -
SKILL.md 2.3 KB
--- name: diff-skill description: | Compare two versions of a skill's instructions to detect degradations and complexity increases. TRIGGER when: user asks to diff, compare, or review changes to a skill's markdown instructions. Asymmetric check — only regressions count. Additions, clarifications, and strengthenings are not degradations. Compares HEAD → working tree by default. Walks the full reachable file set from SKILL.md via markdown links. Produces a report file under docs/reviews/diff-skill/ and an inline summary. --- # Diff Skill Instructions **Goal: Detect whether an edit to a skill's markdown instructions introduced degradations or made the skill harder for an LLM to follow.** Two judgment axes: 1. **Degradation (asymmetric)** — load-bearing instruction dropped, constraint weakened, verification step removed, scope narrowed, required output dropped, or reference broken. Content relocated but preserved is neutral. 2. **Complexity** — split into _regressions_ (introduced or worsened by the edit, affects verdict) and _pre-existing advisories_ (exist regardless of the edit, surfaced as improvement opportunities, does NOT affect verdict). ## Conventions - **Read capy knowledge base conventions** at [shared-capy-knowledge-protocol.md](shared-capy-knowledge-protocol.md). ## Required Outputs - [ ] Report written to `docs/reviews/diff-skill/<slug>-<sha-a>-<sha-b>.md` - [ ] Inline summary presented (under 10 lines: verdict, finding counts, report path) - [ ] Capy indexed under `kk:review-findings` if any degradation or complexity regression findings exist (skip on clean results and pre-existing advisories) ## Invocation ``` /kk:diff-skill <skill-name> ``` Convenience shortcut: resolves `klaude-plugin/skills/<skill-name>/SKILL.md`. If not found, asks the user for the skill directory path. Defaults: `HEAD` (before) → working tree (after). User can specify different refs in the prompt. ## Workflow **Mandatory order — load instructions before acting on subject matter.** The phases below are strictly sequential. Do not read skill content, build file sets, or produce judgments until you have loaded and internalized the full process file. The only early contact with the target skill is its name and SKILL.md path — enough to validate, not enough to judge. See [diff-process.md](diff-process.md) for the detailed step-by-step process.
Comments (0)
Sign in to join the conversation.
Reviews (0)
No reviews yet.
No comments yet.