worktrail-handoff

Capture a discovered problem, gap, tech debt, or deferred work into a local work queue so a future agent session can pick it up cold. Use mid-session whenever you set work aside instead of doing it now — a fix you judge out of scope for this PR, work that belongs in a follow-up or a separate/later PR, an item you're deferring, or something worth fixing you won't tackle now — so the outstanding item isn't lost without derailing current work; can be called multiple times per session. Trigger phrases: "defer this", "item deferred", "out of scope for this PR", "follow-up work", "leave for another PR", "capture for later", "outstanding item". This skill captures only. Picking a brief back up is the front door's job: worktrail-go <brief-id>.

Quality

85%

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

78%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 delivers an excellently sequenced, executable workflow with strong validation checkpoints and a clean one-level reference. Its main weakness is conciseness — several rationale and anecdote passages pad what could be leaner guidance.

Suggestions

Trim the justification paragraphs that explain why a second path is bad (e.g. 'a second documented path is how the queue ended up with two half-true answers') to a one-line rule; the model does not need the history to follow the instruction.

Move the dated brief 20260817-... postmortest anecdote out of the main workflow prose and into a short 'old patterns / lessons' note or drop it, since the embedded specific date and id penalize conciseness without adding executable guidance.

Reduce the inlined Document format field summary and point earlier to references/handoff-template.md so field rules live in only one place.

Dimension	Reasoning	Score
Conciseness	The body is accurate and well-organized, but several passages over-explain rationale a model could infer (e.g. the long 'a second documented path is how the queue ended up with two half-true answers' justification at lines 33–34 and the dated post-mortest anecdote at lines 137–139), which is padding relative to a lean reference style.	3 / 5
Actionability	It provides copy-paste-ready CLI invocations with full flag sets for every step (worktrail-check-duplicate-brief, worktrail-handoff, worktrail-work-queue link/triage, worktrail-decision list/show/answer) and concrete examples of the produced brief path and id, covering the common cases.	5 / 5
Workflow Clarity	The capture workflow is explicitly sequenced (Step 1, 1.5, 2, 3) with a pre-write validation/duplicate-check checkpoint, an AskUserQuestion decision gate, explicit fail-open behavior for headless runs, and a 'do not hand-write a fallback' error path — a clear sequence with explicit validation and feedback loops.	5 / 5
Progressive Disclosure	The body is an overview that offloads the detailed field rules and a full example to a single one-level reference (references/handoff-template.md), but some of that field-level detail is also inlined in the Document format section, so it sits just below the ideal fully-split structure.	4 / 5
	Total	17 / 20 Passed

Description

91%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 is strong: it states the single concrete capture action, gives comprehensive natural trigger phrases, answers both what and when, and draws a crisp boundary against the related resume skill. Its only mild gap is that it describes one capture action rather than a broad set of concrete actions.

Dimension	Reasoning	Score
Specificity	Names a concrete action ('Capture a discovered problem, gap, tech debt, or deferred work into a local work queue') plus the multiple shapes work can take (out-of-scope fix, follow-up PR, deferred item), but the action set is essentially one capture operation rather than a list of several distinct concrete actions, so it sits between the 3 and 5 anchors.	4 / 5
Completeness	It answers 'what' (capture deferred work into a local queue) and 'when' (explicit 'Use mid-session whenever you set work aside' plus concrete trigger phrases), and even scopes the boundary ('This skill captures only'), matching the anchor that requires both what and when with concrete trigger phrases.	5 / 5
Trigger Term Quality	An explicit 'Trigger phrases' block enumerates seven natural user utterances ('defer this', 'out of scope for this PR', 'follow-up work', 'capture for later', 'outstanding item'), giving comprehensive coverage of synonyms users would actually say.	5 / 5
Distinctiveness Conflict Risk	It carves a clear niche (capture-only) and explicitly distinguishes itself from the sibling skill ('Picking a brief back up is the front door's job: worktrail-go <brief-id>'), so it is unlikely to fire for the resume-work path.	5 / 5
	Total	19 / 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
allowed_tools_field	'allowed-tools' contains unusual tool name(s)	Warning
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	14 / 16 Passed

Repository: behindthedash/worktrail
Path: skills/worktrail-handoff/SKILL.md
Commit: ca98247

Reviewed: ~3 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.