CtrlK
BlogDocsLog inGet started
Tessl Logo

he-reconcile

Analyze repo, tracker, PR, validation, session, and .harness evidence. Use when multi-stage Harness Engineering work needs safe resume routing.

72

Quality

Does it follow best practices?

Impact

No eval scenarios have been run

SecuritybySnyk

Passed

No known issues

SKILL.md
Quality
Evals
Security

Quality

Content

92%

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

The content is concise, highly actionable, and workflow-clear for a routing skill. The weakest dimension is progressive disclosure: several external reference paths are broken and one policy line is duplicated.

Suggestions

Fix or remove the six ../../references/*.md links (subagent-call-contract, bluf-review-contract, visual-reference-contract, stage-arc-boundary-contract, deferred-context-index, closure-mutation-contract) — they currently point to a shared location that does not exist alongside this skill.

Deduplicate the "context-disposition policy" sentence, which appears verbatim in both Gotchas and References; reference it once instead.

Resolve the stray bullet ("- See references/hot-path-folded-context.md...") that interrupts the numbered Procedure list at step 4 so the sequence reads cleanly.

DimensionReasoningScore

Conciseness

The body is lean and dense — short sectioned lists with no concept explanations Claude already knows and no padding; every section earns its tokens, matching the lean/efficient anchor.

3 / 3

Actionability

For an instruction-only routing skill the guidance is concrete and specific: named routing targets (he-brainstorm, he-spec, he-plan, etc.), enumerated output fields, and explicit status enums (pass/fail/blocked; provenance found/not_found/blocked/not_applicable); per scoring notes, absence of code is not penalized when guidance is this actionable.

3 / 3

Workflow Clarity

A numbered Procedure (1-4) is paired with explicit validation checkpoints ("Fail fast", gates reported as pass/fail/blocked, "stop with blocked_reason") and a Failure Handling loop, matching the clear-sequence-with-validation anchor.

3 / 3

Progressive Disclosure

Sections are organized with clearly signaled one-level-deep references (e.g., "See references/hot-path-folded-context.md"), and the local bundle files exist, but six ../../references/*.md paths point outside the bundle to a non-existent shared location, and the context-disposition line is duplicated in Gotchas and References — organization could be tighter.

2 / 3

Total

11

/

12

Passed

Description

85%

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 complete, with a clear distinct niche and an explicit Use-when trigger. Its main weakness is trigger-term quality: the keywords are technical jargon a user is unlikely to say naturally.

Suggestions

Add natural-language trigger phrasings users might actually say (e.g., "resume interrupted multi-stage work", "figure out which stage to continue", "reconcile conflicting plan and session evidence") alongside the technical terms.

Soften jargon like "safe resume routing" and ".harness evidence" with plainer equivalents so the description reads as something a user would naturally request.

DimensionReasoningScore

Specificity

Lists multiple concrete actions and evidence sources — "Analyze repo, tracker, PR, validation, session, and .harness evidence" — matching the anchor that names several specific concrete actions.

3 / 3

Completeness

Clearly answers both what ("Analyze ... evidence") and when via the explicit "Use when multi-stage Harness Engineering work needs safe resume routing" clause, matching the top anchor.

3 / 3

Trigger Term Quality

Terms like "multi-stage Harness Engineering work", ".harness evidence", and "safe resume routing" are domain-relevant but jargon-heavy; a user would be unlikely to phrase a need this naturally, matching the anchor with some relevant keywords missing common variations.

2 / 3

Distinctiveness Conflict Risk

The niche is distinct — Harness Engineering resume/reconcile routing with .harness evidence — making it unlikely to trigger for the wrong skill.

3 / 3

Total

11

/

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
jscraik/Agent-Skills
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.