sy-reconcile

Analyze stale or conflicting lifecycle state by separating local, PR, CI, review, tracker, artifact, and session truth. Use when status is confused, work resumed after drift, evidence lanes disagree, or a closeout claim may be stale.

Quality

77%

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 ./Plugins/synaipse-harness/skills/sy-reconcile/SKILL.md

Quality

Content

71%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, lean orchestration skill with a clear sequenced procedure, an explicit validation checkpoint, and clean one-level-deep references to real bundle files. Its weakest point is actionability: key concepts ('work owned by reconcile', 'previous-stage artifact') are referenced but not defined inline.

Suggestions

Define what 'the work owned by reconcile' actually is inline (or point to the specific contract section) so the core action is unambiguous without loading external files.

Remove the verbatim duplication of the description's trigger sentence in 'When to use' or replace it with stage-specific guidance that adds new information.

Add one concrete example of a resolved reconcile handoff artifact (with sample evidence_refs and next_stage) to lift actionability toward executable guidance.

Dimension	Reasoning	Score
Conciseness	The body is lean with terse bullets and no concept explanations Claude already knows, but the 'When to use' section duplicates the description's trigger sentence verbatim and 'Handoff' reiterates earlier points, so minor trimming is possible. Not a 5 due to that redundancy.	4 / 5
Actionability	It gives some concrete guidance (explicit deliverable schema fields, exact status vocabulary pass/fail/blocked/not_checked, a fail-fast rule), but core abstractions like 'the work owned by reconcile' and 'the previous-stage artifact' are not defined inline and rely on external context. This incompleteness keeps it at 3 rather than 4.	3 / 5
Workflow Clarity	The five-step Procedure is clearly sequenced and the Validation section is an explicit checkpoint ('stop at the first failed required gate... do not proceed... until resolved or waived') with blocker classification and a smallest-recovery-step handoff. Not a 5 because the validation is procedural guidance rather than a concrete validate→fix→retry command loop.	4 / 5
Progressive Disclosure	The body is a concise overview with a clearly signaled References section pointing one level deep to four real, descriptively labeled files (contract, evals, task-profile, source-context), all of which exist; content is appropriately split for easy navigation.	5 / 5
	Total	16 / 20 Passed

Description

83%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.

A strong description that clearly states a concrete action, enumerates the evidence lanes it operates on, and gives multiple natural 'Use when' triggers in third person. Main gap is single-action breadth and a few missing trigger synonyms.

Dimension	Reasoning	Score
Specificity	The verb 'Analyze stale or conflicting lifecycle state by separating' is concrete and it enumerates seven specific truth lanes (local, PR, CI, review, tracker, artifact, session), giving broad coverage of the action's scope. It stops short of score 5 because there is effectively one action (separate/classify) rather than multiple distinct concrete actions.	4 / 5
Completeness	It explicitly answers both 'what' (analyze/separate lifecycle state across truth lanes) and 'when' (Use when status is confused, drift, disagreeing lanes, stale closeout) with concrete trigger phrases, matching the score-5 anchor. Voice is third person, so no penalty applies.	5 / 5
Trigger Term Quality	'Use when status is confused, work resumed after drift, evidence lanes disagree, or a closeout claim may be stale' supplies several natural phrases a user would actually say. Not a 5 because synonyms/common variations (e.g. 'out of sync', 'stale state') are not covered.	4 / 5
Distinctiveness Conflict Risk	The reconcile/lifecycle-state-evidence niche is fairly distinct with specific triggers, but 'analyze status' framing could mildly overlap with general debugging or status-checking skills, so it is mostly distinct rather than fully conflict-free.	4 / 5
	Total	17 / 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: jscraik/Agent-Skills
Path: Plugins/synaipse-harness/skills/sy-reconcile/SKILL.md
Commit: f1f2f21

Reviewed: ~5 hours 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.