CtrlK
BlogDocsLog inGet started
Tessl Logo

harness-progress

Generate a Progress Tracker HTML for non-engineer vibecoders to glance at session progress (cc:WIP / cc:TODO / cc:完了 counts, percentage, elapsed/estimated minutes, cost so far/estimate, drift alerts). Uses Plans.md as source of truth, renders a single-file HTML with auto-regeneration support. Use when user asks for progress overview, session status snapshot, dashboard, or says: progress tracker, 進捗確認, 進捗ボード, dashboard. Do NOT load for: actual implementation, code review, release work.

69

Quality

86%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Passed

No findings from the security scan

The canonical home for this skill is harness-progress in Chachamaru127/claude-code-harness

SKILL.md
Quality
Evals
Security

Quality

Content

72%

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 skill body with concrete commands and a clear execution flow plus failure-mode handling. It loses points for narrative/phase-roadmap padding and for lacking an explicit validation checkpoint in the main flow, and the referenced script/schema files are absent from the bundle.

Suggestions

Trim the framing prose (triplet narrative, restated Mission, 65.4.x phase roadmap) so the body stays focused on execution; keep only the Mission one-liner.

Add an explicit validation checkpoint in the Execution Flow, e.g. verify the snapshot JSON conforms to progress-snapshot.v1 before rendering, and fail fast with a clear message if a referenced script is missing.

Either ship the referenced files (scripts/progress-snapshot.sh, scripts/render-html.sh, scripts/plan-brief-open.sh, and the schema JSON) in the bundle or note that they are implemented in a later phase so the one-level-deep references actually resolve.

DimensionReasoningScore

Conciseness

Mostly efficient (tables, bash, a YAML schema preview) but padded with narrative framing ("3rd surface of the cognitive-load HTML triplet", restated Mission prose, and a phase-roadmap of 65.4.x items) that Claude does not need to execute the task.

2 / 3

Actionability

Provides concrete, copy-paste bash for each step (basename/git for PROJECT_NAME, scripts/progress-snapshot.sh with --plans/--project flags, render-html.sh with --template/--data/--out, plan-brief-open.sh) plus a complete YAML schema spec.

3 / 3

Workflow Clarity

Steps are clearly numbered (Step 0–3) with a dedicated Failure modes table, but the main flow has no explicit validate-before-proceed checkpoint (e.g., verify the snapshot JSON is valid before rendering), leaving verification implicit.

2 / 3

Progressive Disclosure

Well-organized into clear sections with one-level-deep, clearly signaled references (schema spec delegated to schemas/progress-snapshot.v1.schema.json, scripts invoked inline), giving easy navigation. Note: the referenced scripts and schema file are not present in the supplied bundle.

3 / 3

Total

10

/

12

Passed

Description

100%

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, third-person description that states concrete capabilities, gives natural trigger phrasings in two languages, and explicitly scopes when to (and not to) load. No vague fluff or over-claims.

DimensionReasoningScore

Specificity

Lists multiple concrete actions — "Generate a Progress Tracker HTML", "renders a single-file HTML", aggregating "cc:WIP / cc:TODO / cc:完了 counts, percentage, elapsed/estimated minutes, cost so far/estimate, drift alerts" — which matches the multi-action anchor.

3 / 3

Completeness

Explicitly answers both what (generate single-file progress HTML from Plans.md) and when ("Use when user asks for progress overview..."), plus a "Do NOT load for" exclusion clause.

3 / 3

Trigger Term Quality

Gives natural user phrasings ("progress overview, session status snapshot, dashboard" and "progress tracker, 進捗確認, 進捗ボード") covering both English and Japanese variations a user would actually say.

3 / 3

Distinctiveness Conflict Risk

A clear niche (Plans.md/cc: progress dashboard) combined with explicit negative triggers ("Do NOT load for: actual implementation, code review, release work") makes misfiring unlikely.

3 / 3

Total

12

/

12

Passed

Validation

87%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation14 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

relative_links

Relative link issues: 1 missing, 1 deeper-than-1-level

Warning

referenced_paths_exist

Referenced path issues: 4 missing

Warning

Total

14

/

16

Passed

Repository
Chachamaru127/claude-code-harness
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.