reskill

Extract durable operating knowledge before slimming or replacing team charters

Quality

64%

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

Fix and improve this skill with Tessl

tessl review fix ./.copilot/skills/reskill/SKILL.md

Quality

Content

75%Weight 40%Scale 1-5

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

The content is a lean, operationally precise procedure: explicit step sequencing, measurable targets, a target-format template, conflict-resolution ordering, and an anti-patterns guardrail list. The only meaningful weaknesses are a few vague references to unnamed commands and templates and the absence of an explicit re-validation loop after the destructive trim step.

Dimension	Reasoning	Score
Conciseness	The body is imperative and dense — concrete thresholds ('target ≤1.5KB per agent', 'target ≤8KB per agent') and rules with no padding or explanation of concepts Claude already knows; only minor sections (e.g., 'Source and Mirror Discipline') could be tightened further.	4 / 5
Actionability	Highly actionable for an instruction-only skill: exact destination paths (.squad-templates/skills/, .github/skills/, .squad/skills/), a copy-paste Minimal Charter Template, concrete trim rules, a report table format, and an ordered conflict-resolution list. Minor gaps remain, e.g. 'run the repository's skill-template sync command' never names the command, and 'Follow the skill template format' does not point to that template.	4 / 5
Workflow Clarity	The four-step Audit → Extract → Trim → Report sequence is clearly ordered and includes checkpoints (reconcile candidates against current source/tests/docs before preserving, verify root/CLI/SDK mirrors are byte-identical, output before/after byte measurements). However, the destructive trim step has no explicit post-trim re-validation loop (e.g. re-checking that no retirement-critical knowledge was lost), leaving a minor validation gap.	4 / 5
Progressive Disclosure	A single well-sectioned SKILL.md with clear Context / Process / Patterns / Anti-Patterns organization, no nested or dangling references, and content (template, patterns, anti-patterns) appropriately inline for its size. At ~120 lines it exceeds the simple-skill threshold, so a couple of the longer pattern sections could arguably move to reference files, keeping it just short of a 5.	4 / 5
	Total	16 / 20 Passed

Description

53%Weight 40%Scale 1-5

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, in third person, and names a distinct niche, but it functions as a half-sentence 'what' with no 'when' trigger clause and omits the natural trigger phrases ('reskill', 'optimize context', 'slim down charters') that the skill body itself documents. It reads as a terse title rather than a complete activation surface.

Suggestions

Add an explicit 'Use when...' trigger clause, e.g. 'Use when the user says "reskill", "optimize context", "slim down charters", or before re-casting a team.'

Enumerate the concrete actions the skill performs — audit charters/histories, extract shared patterns into skills, trim charters to size targets, and report savings — instead of the single 'extract' verb.

Include the synonyms users would naturally say (reskill, charter bloat, context overhead) so the skill triggers on real phrasing, not just the formal terms.

Dimension	Reasoning	Score
Specificity	The description names the domain ('team charters') and one concrete action ('Extract durable operating knowledge'), but 'slimming or replacing' is timing context rather than additional enumerated actions, so coverage is not comprehensive.	3 / 5
Completeness	It has a clear 'what' (extract durable operating knowledge from team charters before slimming/replacing them) but no 'Use when...' clause or equivalent explicit trigger guidance, which caps completeness at 3 per the judging guidelines.	3 / 5
Trigger Term Quality	'team charters', 'slimming', and 'replacing' are relevant keywords, but the natural phrases a user would actually say — 'reskill', 'optimize context', 'slim down charters', 'charter bloat' (all listed in the body) — are missing from the description.	3 / 5
Distinctiveness Conflict Risk	'Team charters' plus the per-agent context niche is a distinct trigger surface with only minor overlap risk against generic document- or code-slimming skills; it is not specific enough to be fully conflict-free.	4 / 5
	Total	13 / 20 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
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	15 / 16 Passed

Repository: bradygaster/squad
Path: .copilot/skills/reskill/SKILL.md
Commit: 29e69f5

Reviewed: 5 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.