CtrlK
BlogDocsLog inGet started
Tessl Logo

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.

60

Quality

68%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./agents/skills/sync-findings/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

70%

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

The workflow is clearly sequenced with explicit save-first and close-only-what's-closed checkpoints, and the file is well-organized with signaled one-level references, but it carries redundant rationale and mixes concrete steps with abstract guidance.

Suggestions

Collapse the Step 3 rationale paragraph and the restated "Save-first is mandatory" rule into a single concise statement to reduce redundancy.

Tighten abstract steps 4–5 with concrete specifics (e.g., name the PR comment fields to capture, the thread-state fields to update) instead of "Map comments to findings, update sources and statuses".

Either inline the canonical findings schema fields or confirm the shared reference files exist at ../shared/references/ so the externalized schema is actually reachable.

DimensionReasoningScore

Conciseness

Mostly efficient and well-structured, but the rationale paragraph ("This rule exists because diving straight into...") and the restated "Save-first is mandatory" Rules section duplicate Step 3 and could be tightened.

2 / 3

Actionability

Step 3 is concrete (path/findings.md, ## Open Findings, field list, needs-user-decision), but Steps 4–5 and the Role section use abstract phrasing ("Map comments to findings, update sources and statuses") and the canonical schema is referenced externally rather than given inline.

2 / 3

Workflow Clarity

A clear 6-step sequence with an explicit gating checkpoint ("Only after findings.md is up to date may you start...") and a verification gate before the destructive thread-resolve action ("Close only what is clearly closed").

3 / 3

Progressive Disclosure

The body is organized into clearly labeled sections (Role, URL Input, Path Input, Workflow, Rules) with one-level-deep shared references signaled at the top; note the cited ../shared/references/*.md files are not present in the bundle.

3 / 3

Total

10

/

12

Passed

Description

67%

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 specific and occupies a clear niche, but it omits an explicit "Use when..." trigger and leans on internal jargon, leaving its "when to use" guidance only implied.

Suggestions

Add an explicit "Use when..." clause naming natural user triggers (e.g., "Use when the user asks to sync or refresh the findings record against local review docs or a GitHub PR").

Soften jargon with user-spoken phrasings such as "refresh findings", "sync review notes", or "reconcile findings with the PR".

Keep the variable defaults (path=infer, url=local-only) but move them after the trigger clause so the opening sentence leads with capability and trigger.

DimensionReasoningScore

Specificity

Lists several concrete actions — "Sync the findings record against local review artifacts and optionally a GitHub PR", "sync against both remote PR state and local state", "Confirm effective variables before starting" — rather than vague language.

3 / 3

Completeness

The "what" is clearly stated, but there is no "Use when..." clause or equivalent explicit trigger guidance, so completeness is capped at 2 per the rubric guidelines.

2 / 3

Trigger Term Quality

Relevant domain terms ("findings record", "review artifacts", "GitHub PR") are present, but the phrasing is jargon-heavy with no "Use when..." trigger and missing common user-spoken variations.

2 / 3

Distinctiveness Conflict Risk

"Sync the findings record against local review artifacts and optionally a GitHub PR" carves a clear niche with distinct triggers, unlikely to fire for unrelated skills.

3 / 3

Total

10

/

12

Passed

Validation

100%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
Agenta-AI/agenta
Reviewed

Table of Contents

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.