provider-research-digest

Render the digest for one provider-research date from every report on disk, topped with authored highlight bullets; publishing is scripts/provider-watch/publish.py's job, run outside this skill

Quality

71%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./.claude/skills/provider-research-digest/SKILL.md

Quality

Content

86%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 body is a tight, actionable, well-sequenced workflow with concrete commands and strong guardrails around the dangerous publish step; its only soft spots are slight repetition of the no-publish boundary and the absence of a final-output verification checkpoint.

Dimension	Reasoning	Score
Conciseness	The body is efficient with copy-paste-ready commands and assumes Claude's competence; the only trimming opportunity is the 'publishes nothing' boundary, which is restated in the intro, Step 4, and the Guardrails.	4 / 5
Actionability	It provides fully executable, copy-paste-ready commands with concrete arguments (e.g. 'uv run python scripts/provider-watch/digest.py --reports _reports --date <RUN_DATE> --out <scratch>/digest-draft.md') covering each phase of the workflow.	5 / 5
Workflow Clarity	Steps 1-4 are clearly sequenced with a precondition validation in Step 1 ('Stop with a clear error if no ... exists') and a safe hand-off in Step 4, but there is no final-output verification or explicit feedback loop on the rendered digest.	4 / 5
Progressive Disclosure	This is a well-organized, sub-50-line single-purpose skill with clear sections (Arguments, Instructions, Guardrails) and no need for external reference files, meeting the simple-skill exception for progressive disclosure.	5 / 5
	Total	18 / 20 Passed

Description

57%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 states a clear, specific purpose and a strong boundary (publishing is out of scope), but lacks an explicit 'Use when...' trigger clause and relies on a single project-specific term, capping completeness and trigger-term quality at 3.

Suggestions

Add an explicit trigger clause, e.g. 'Use when you need to assemble the provider-research digest for a date from the reports checkout.'

Broaden trigger terms with natural synonyms (e.g. 'digest', 'summary', 'daily report', 'highlights') so users have more entry phrases.

Optionally note the date argument in the description ('renders the digest for a given date') to surface the primary parameter.

Dimension	Reasoning	Score
Specificity	It names the domain and two concrete actions ('Render the digest for one provider-research date from every report on disk' and 'topped with authored highlight bullets'), but stops at 1-2 actions rather than comprehensive coverage; the publishing clause describes a boundary, not a capability of this skill.	3 / 5
Completeness	The 'what' is clear (render a date digest topped with authored highlights), but there is no 'Use when...' clause or equivalent explicit trigger guidance, so completeness is capped at 3 with only a weakly implied 'when'.	3 / 5
Trigger Term Quality	It carries relevant keywords ('provider-research', 'digest', 'report', 'highlight bullets') but relies on the narrow project term 'provider-research' and offers no common synonyms or variations a user might naturally say.	3 / 5
Distinctiveness Conflict Risk	It occupies a clear, narrow niche — rendering the provider-research digest from on-disk reports — and, as a disable-model-invocation slash skill, is extremely unlikely to trigger for the wrong skill.	5 / 5
	Total	14 / 20 Passed

Validation

87%

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 — 14 / 16 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning
referenced_paths_exist	Referenced path issues: 4 missing, 4 deeper-than-1-level	Warning

	Total	14 / 16 Passed

Repository: pipecat-ai/pipecat
Path: .claude/skills/provider-research-digest/SKILL.md
Commit: baf1f16

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.