trellis-finish-work

Wrap up the current session: verify quality gate passed, remind user to commit, archive completed tasks, and record session progress to the developer journal. Use when done coding and ready to end the session.

Quality

84%

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

76%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, actionable four-step finish-work workflow with concrete commands and a pre-flight sanity gate. Its main gap is the absence of a post-archive/journal verification feedback loop, which caps workflow clarity for this batch/destructive operation.

Suggestions

Add an explicit verification step after archiving and journaling (e.g., re-run get_context.py to confirm the active task is gone and the journal entry landed), with a fix-and-retry loop if verification fails — this would lift the workflow-clarity cap for the batch/destructive archive operation.

Tighten Step 2 by collapsing the three heuristic bullets and trimming the auto-commit explanatory aside, since Claude can infer the routing from the path classification.

Surface the final expected git log order as an explicit verification checklist item so Claude can confirm the session landed in the intended commit sequence before declaring done.

Dimension	Reasoning	Score
Conciseness	Mostly lean with executable command blocks and no explaining of basic git/python concepts, but the Step 2 heuristics and a few explanatory asides ('those are managed by add_session.py ... auto-commits') could be trimmed; fits the 'efficient, minor over-explanation' anchor rather than the 5.	4 / 5
Actionability	Provides fully executable, copy-paste-ready commands for each step (get_context.py, git status --porcelain, task.py archive, add_session.py with example args) plus concrete routing/commit-message guidance; matches the top anchor.	5 / 5
Workflow Clarity	The 4-step sequence is clear with a Step 2 pre-flight gate, but archiving tasks and journaling are batch/destructive auto-commit operations with no post-action validate/retry feedback loop; per the batch-operation cap, workflow_clarity cannot exceed 3.	3 / 5
Progressive Disclosure	Well-organized into clearly headed steps with no nested references and all content appropriately self-contained, but the body slightly exceeds the under-50-line simple-skill threshold and has no external file references to signal; fits the 'good structure, minor gaps' anchor.	4 / 5
	Total	16 / 20 Passed

Description

92%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, specific description that clearly states four concrete wrap-up actions and an explicit, natural trigger clause. The only minor weakness is limited trigger-term synonym coverage.

Dimension	Reasoning	Score
Specificity	Lists four concrete actions ('verify quality gate passed', 'remind user to commit', 'archive completed tasks', 'record session progress to the developer journal'), matching the comprehensive multi-action anchor; not 4 because coverage is complete rather than having minor gaps.	5 / 5
Completeness	Explicitly answers both what (the four wrap-up actions) and when ('Use when done coding and ready to end the session') with a concrete trigger phrase, matching the top anchor; not 4 because the 'when' is explicit and specific rather than merely adequate.	5 / 5
Trigger Term Quality	The trigger 'Use when done coding and ready to end the session' is a natural user phrase, but it offers a single phrasing with limited synonym coverage; fits the 'good keyword coverage, a few natural terms missing' anchor rather than the 5's comprehensive synonym set.	4 / 5
Distinctiveness Conflict Risk	Occupies a clear 'session wrap-up / finish work' niche and even notes that commits happen elsewhere, minimizing overlap with commit/coding skills; matches the minimal-conflict-risk anchor.	5 / 5
	Total	19 / 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: EcoPasteHub/EcoPaste
Path: .kiro/skills/trellis-finish-work/SKILL.md
Commit: 5139d30

Reviewed: 19 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.