skill-authoring-workflow

Turn raw PM content into a compliant, publish-ready skill. Use when creating or updating a repo skill without breaking standards.

Quality

81%

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

92%

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 tight, executable workflow with explicit phase sequencing and a hard validation checkpoint, scoring top marks on conciseness, actionability, and workflow clarity. Progressive disclosure is the weakest dimension: references are flat lists of filenames/URLs with no annotation of what each provides.

Suggestions

Annotate each References entry, e.g. '`docs/Building PM Skills.md` — section-order and metadata rules' and '`scripts/check-skill-metadata.py` — validates frontmatter limits', so the reader knows what each file holds before opening it.

Signal the facilitation handoff inline with a one-line map (entry modes, turn cadence, progress labels) rather than only pointing at ../workshop-facilitation/SKILL.md.

For the external Anthropic PDF, note what it covers (skill structure best practices) so the link is self-describing.

Dimension	Reasoning	Score
Conciseness	The body is lean, assumes Claude knows git/validation basics, and stays mostly to commands and checklists with no explanatory padding about what skills or bash are; the small amount of rationale (e.g. the $ARGUMENTS note) earns its place.	3 / 3
Actionability	It gives executable, copy-paste-ready commands at every phase (find-a-skill.sh, add-a-skill.sh, test-a-skill.sh, check-skill-metadata.py) plus a concrete worked example with expected results, matching the fully-executable anchor.	3 / 3
Workflow Clarity	Six phases are explicitly sequenced (Preflight -> Generate -> Tighten -> Validate -> Integrate -> Package), Phase 4 is a dedicated validation checkpoint with strict-run commands, and the Definition of Done checklist and anti-pattern give error-recovery feedback loops.	3 / 3
Progressive Disclosure	The body is well-sectioned and keeps references one level deep, but every reference (README.md, scripts/.sh, docs/, an external PDF) is an opaque repo/URL pointer with no inline signaling of what each holds, and the facilitation protocol is delegated out without summarizing navigation, so structure is good but signaling is partial.	2 / 3
	Total	11 / 12 Passed

Description

70%

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 cleanly pairs a what-statement with an explicit 'Use when' trigger and is concise and third-person, so it clears completeness. It loses points on specificity and trigger coverage because it bundles the workflow into a single abstract action and omits natural phrases like 'author' or 'SKILL.md'.

Suggestions

Replace the single abstract action with two or three concrete verbs, e.g. 'Draft, validate, and publish repo skills from raw PM content'.

Add natural trigger terms a user would actually say, such as 'author a skill', 'write a SKILL.md', or 'turn notes/workshop content into a skill'.

Tighten distinctiveness by naming the repo context, e.g. '...a repo skill without breaking the PM skills repo standards'.

Dimension	Reasoning	Score
Specificity	It names the domain (PM content, repo skill) and a concrete action ('turn... into a compliant, publish-ready skill') but lists only one high-level action rather than multiple specific concrete steps, matching the 'names domain and some actions' anchor.	2 / 3
Completeness	It explicitly answers what it does ('Turn raw PM content into a compliant, publish-ready skill') and when to use it via an explicit 'Use when creating or updating a repo skill...' clause, satisfying the both-what-and-when anchor.	3 / 3
Trigger Term Quality	'creating or updating a repo skill' are relevant terms a user might say, but it lacks common phrasings like 'author a skill', 'write a SKILL.md', or 'skill from notes', so coverage is partial rather than strong.	2 / 3
Distinctiveness Conflict Risk	The skill-authoring niche is fairly distinct, but 'creating or updating a repo skill' could still overlap with sibling authoring skills (e.g. build-a-skill, add-a-skill), so it is not yet a conflict-free niche.	2 / 3
	Total	9 / 12 Passed

Validation

81%

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 — 13 / 16 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning
relative_links	Relative link issues: 1 suspicious	Warning
referenced_paths_exist	Referenced path issues: 15 missing	Warning

	Total	13 / 16 Passed

Repository: deanpeters/Product-Manager-Skills
Path: skills/skill-authoring-workflow/SKILL.md
Commit: 9971018

Reviewed: 3 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.