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.

51

Quality

56%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Failed to scan

The risk profile of this skill

Fix and improve this skill with Tessl

tessl review fix ./Plugins/harness-engineering/skills/he-reconcile/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

50%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-sectioned, safety-conscious routing skill that clearly delineates scope, handoff targets, and output structure. It loses points for repeated reference pointers, broken external reference paths, and a procedure that stays high-level rather than giving concrete executable mechanics.

Suggestions

Collapse the repeated "See references/hot-path-folded-context.md for folded X detail" pointers into a single consolidated pointer to avoid near-duplicate lines across sections.

Resolve or remove the ../../references/*.md links that do not exist in the bundle so navigation is not broken.

Tighten the Procedure into explicit, complete steps with a concrete validation feedback loop (reconstruct -> validate gates -> route or blocked_reason) instead of a trailing step 4.

DimensionReasoningScore

Conciseness

The body is mostly lean and assumes Claude's competence (no basic-concept padding), but the "See references/hot-path-folded-context.md for folded ... detail" line is repeated ~6 times and the context-disposition policy sentence is duplicated verbatim (Gotchas and References), which is noticeable padding that could be tightened.

3 / 5

Actionability

Guidance is concrete in places (enumerated output fields, an explicit handoff routing table, pass/fail/blocked gates), but the core procedure stays abstract ("Reconstruct lifecycle state from ... evidence", "Resolve only enough context") with no executable mechanics or specific read paths, leaving key details implicit.

3 / 5

Workflow Clarity

A numbered procedure and dedicated Validation/Failure Handling sections provide checkpoints (pass/fail/blocked, blocked_reason), but the procedure is only four steps with step 4 trailing off into a reference bullet, and the validation feedback loop (fail -> fix -> retry) is implied rather than explicitly sequenced.

3 / 5

Progressive Disclosure

SKILL.md acts as an overview pointing to one-level-deep bundle files (contract.yaml, evals.yaml, hot-path-folded-context.md), but several referenced ../../references/*.md paths do not resolve in the bundle and the hot-path file is redundantly pointed to from nearly every section, weakening navigation.

3 / 5

Total

12

/

20

Passed

Description

62%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 focused, third-person description that explicitly pairs a concrete "what" with an explicit "Use when" trigger and carves out a clear niche. It is held back by reliance on a single action verb and jargon-bound trigger terms that lack natural synonyms.

Suggestions

Add one or two more distinct verbs (e.g., 'reconstruct', 'route', 'reconcile') so the capability reads as multiple concrete actions rather than one analyze step.

Broaden the trigger with natural variations users might say, such as 'resume stalled work', 'pick up an incomplete HE stage', or 'reconcile stale evidence'.

State the produced outcome explicitly (e.g., 'returns the earliest incomplete stage and a safe next-step route') to sharpen the 'what'.

DimensionReasoningScore

Specificity

Names the domain and enumerates concrete evidence sources ("repo, tracker, PR, validation, session, and .harness evidence") plus an implied routing action, but effectively rests on one verb ("Analyze") rather than multiple distinct actions, so it stops short of comprehensive coverage.

3 / 5

Completeness

Both "what" (analyze the listed evidence) and "when" (explicit "Use when..." clause with a concrete trigger) are present and clear, but the "what" could be more specific about the produced outcome to fully reach the top anchor.

4 / 5

Trigger Term Quality

The trigger "Use when multi-stage Harness Engineering work needs safe resume routing" is relevant within the HE niche, but the keywords are domain jargon with no common synonyms or variations a user would naturally vary.

3 / 5

Distinctiveness Conflict Risk

The Harness Engineering reconcile niche with "safe resume routing" triggers is clearly distinct from generic skills, with only minor overlap risk against the other he-* skills it hands off to.

4 / 5

Total

14

/

20

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.