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.

67

Quality

82%

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

SKILL.md
Quality
Evals
Security

Quality

Content

65%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 is well-structured and largely executable, but it references bundle files (scripts, schema, template) that are not present, and the batch HTML-regeneration workflow lacks an explicit validation checkpoint. Fixing the missing bundle and adding a validate step would lift the two lowest dimensions.

Suggestions

Ship the referenced bundle (scripts/progress-snapshot.sh, scripts/render-html.sh, scripts/plan-brief-open.sh, scripts/writing-rule-list.sh, scripts/writing-rule-approve.sh, schemas/progress-snapshot.v1.schema.json, and the progress.html.template) so the signaled references resolve to real files.

Add an explicit validation checkpoint before opening the browser — e.g. after render-html.sh, verify $OUT_PATH is non-empty / valid HTML and surface render-html.sh's exit code before proceeding to Step 3.

Collapse the bilingual Mission quote and the やる/やらない lists, since Quick Reference and the Schema section already convey the same intent, to tighten token efficiency.

DimensionReasoningScore

Conciseness

Mostly efficient with compact schema YAML, numbered steps, and a tight failure-mode table, but the bilingual Mission quote and the 'やる/やらない' lists restate intent already conveyed by Quick Reference, so minor trimming is possible.

4 / 5

Actionability

Step 0–3 give concrete copy-paste bash with real flags and variable assignments, but the referenced scripts (progress-snapshot.sh, render-html.sh, plan-brief-open.sh) are not present in any bundle directory and schema fields are placeholders like '<basename of git repo>', leaving minor gaps.

4 / 5

Workflow Clarity

A clear Step 0→3 sequence with an explicit --no-open conditional and a failure-mode table is present, but there is no validate-before-open checkpoint or feedback loop for this batch HTML-regeneration operation, so workflow clarity is capped at 3 per the batch/destructive guidance.

3 / 5

Progressive Disclosure

Sections are well organized and the schema detail is linked one level deep to ${CLAUDE_SKILL_DIR}/schemas/progress-snapshot.v1.schema.json, but no references/, scripts/, or assets/ bundle directories exist, so the referenced scripts, template, and schema file are not real — structure is good but the signaled references are broken.

3 / 5

Total

14

/

20

Passed

Description

100%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 exemplary: concrete capabilities, natural bilingual trigger phrases, explicit use-when guidance, and a clear exclusion clause. Voice is consistently third person with no over-claims.

DimensionReasoningScore

Specificity

Lists multiple concrete actions — 'Generate a Progress Tracker HTML', aggregate 'cc:WIP / cc:TODO / cc:完了 counts, percentage, elapsed/estimated minutes, cost so far/estimate, drift alerts', and 'renders a single-file HTML with auto-regeneration support' — covering the skill comprehensively.

5 / 5

Completeness

Explicitly answers both what (generate a single-file progress HTML with named metrics from Plans.md) and when ('Use when user asks for progress overview, session status snapshot, dashboard, or says: ...'), and adds an explicit exclusion list.

5 / 5

Trigger Term Quality

Provides natural phrases users would say — 'progress overview', 'session status snapshot', 'dashboard', 'progress tracker' — plus bilingual synonyms 進捗確認 / 進捗ボード, giving comprehensive keyword coverage.

5 / 5

Distinctiveness Conflict Risk

Occupies a clear niche (progress dashboard HTML for non-engineer vibecoders) and the 'Do NOT load for: actual implementation, code review, release work' clause sharply distinguishes it from sibling harness skills, minimizing wrong-skill triggering.

5 / 5

Total

20

/

20

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: 7 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.