sync-findings

Sync the findings record against local review artifacts and optionally a GitHub PR. Accept optional `path` and GitHub PR `url`; when `url` is provided, sync against both remote PR state and local state, otherwise default to local-only sync. Default to `path=infer`. Confirm effective variables before starting.

Quality

74%

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 ./.agents/skills/sync-findings/SKILL.md

Quality

Content

77%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.

A well-structured, mostly lean coordination skill with a clear, well-validated workflow and concrete actionable steps; its main weakness is progressive disclosure, since the shared reference files it points to do not exist and the schema it relies on is not otherwise provided.

Suggestions

Create or restore the referenced files ../shared/references/findings.schema.md and findings.lifecycle.md, or inline the canonical finding schema so Step 3 is self-contained.

Make the shared references clearly signaled (e.g., a dedicated '## References' section with one-line descriptions of what each file provides) rather than a bare list at the top.

Trim the justifying paragraph after Step 3 ('This rule exists because...') since Claude can infer the rationale, nudging conciseness toward 5.

Dimension	Reasoning	Score
Conciseness	The body is lean and largely assumes Claude's competence, with only one mild over-explanation paragraph justifying why the save-first rule exists that could be trimmed.	4 / 5
Actionability	Concrete, executable guidance throughout (canonical schema fields, needs-user-decision marking, path/findings.md usage, thread reply/resolve) with a minor gap: the exact schema format is deferred to a reference file rather than shown inline.	4 / 5
Workflow Clarity	A six-step numbered workflow with an explicit mandatory save-first checkpoint, a feedback loop for ambiguous findings (Step 5), and a clear guardrail for closing only clearly-closed threads (Step 6).	5 / 5
Progressive Disclosure	The body references two shared files at the top, but those paths (../shared/references/findings.schema.md and findings.lifecycle.md) do not exist on disk and no bundle files are present, so the references are dead links and the canonical schema the workflow depends on is unavailable.	3 / 5
	Total	16 / 20 Passed

Description

58%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 clearly communicates what the skill does and is reasonably specific and distinct, but it lacks an explicit 'when to use' trigger clause and is missing common natural trigger-term variations, capping completeness and trigger quality.

Suggestions

Add an explicit 'Use when...' clause naming concrete trigger phrases (e.g., 'Use when syncing review findings against a PR or local docs, or when the user asks to update findings').

Broaden trigger terms with natural synonyms users say — 'review notes', 'pull request comments', 'update findings', 'triage comments'.

Optionally enumerate 1-2 more concrete sub-actions (map comments to findings, resolve closed threads) to push specificity toward comprehensive coverage.

Dimension	Reasoning	Score
Specificity	Names the domain (findings-record sync) and several concrete actions — syncing against local artifacts, remote PR state, and handling path/url variables — but does not enumerate sub-actions like mapping comments or resolving threads, leaving it just below comprehensive.	4 / 5
Completeness	The 'what' is clearly stated, but there is no explicit 'Use when...' trigger clause, so per the rubric 'when' guidance is only weakly implied and completeness is capped at 3.	3 / 5
Trigger Term Quality	Contains relevant keywords ('findings', 'GitHub PR', 'review artifacts', 'sync') but misses common natural variations a user might say such as 'review notes', 'pull request comments', or 'update findings'.	3 / 5
Distinctiveness Conflict Risk	The findings-record sync niche is clearly carved and unlikely to trigger for unrelated skills, with only minor overlap risk against the sibling triage-findings skill.	4 / 5
	Total	14 / 20 Passed

Validation

100%

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 — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: Agenta-AI/agenta
Path: .agents/skills/sync-findings/SKILL.md
Commit: 7a975fb

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.