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.

Quality

81%

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

63%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-structured, mostly actionable body with a clear step sequence and failure-mode table, weakened by internal phase-version noise and by referencing scripts/schemas that are not bundled. Tightening the phase cruft and bundling (or clearly marking as external) the referenced scripts would lift it materially.

Suggestions

Remove internal phase/version bookkeeping (e.g. 'Phase 65.4.3 以降', 'Phase 136.2', '3rd surface of the cognitive-load HTML triplet') and forward references to unimplemented phases; these add tokens without aiding execution.

Bundle the referenced scripts (progress-snapshot.sh, render-html.sh, plan-brief-open.sh) in ./scripts/ and the schema in ./references/ — or explicitly mark them as external project files — so the body's commands are actually executable from the skill package.

Add an explicit validation checkpoint between Step 1 and Step 2 (e.g. verify the snapshot JSON against progress-snapshot.v1 before rendering) to strengthen the workflow's feedback loop.

Dimension	Reasoning	Score
Conciseness	Mostly efficient with tables and code blocks, but laced with internal phase bookkeeping ('Phase 65.4', '65.4.1', '136.2', '140.2', '135.4', '3rd surface of the cognitive-load HTML triplet') and forward references to unimplemented phases that Claude does not need to execute the skill.	3 / 5
Actionability	Steps 0–3 give concrete, copy-paste bash commands with real flags, but those commands invoke scripts (progress-snapshot.sh, render-html.sh, plan-brief-open.sh) that are not bundled in the skill, leaving a minor execution gap.	4 / 5
Workflow Clarity	A clear Step 0→3 sequence with a failure-modes table covering missing Plans.md, empty task lists, and missing state files; minor gap is the absence of an explicit validate-snapshot checkpoint before rendering.	4 / 5
Progressive Disclosure	Sections are well organized (Quick Reference, Mission, Schema, Execution Flow, Failure modes, Related) and the schema is inlined compactly, but the body heavily references scripts and a schema file that are not present in any bundle directory, so references are not actually resolvable.	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.

An exemplary description: concrete capabilities, explicit what/when guidance, bilingual trigger synonyms, and a clear negative-trigger boundary. Voice is appropriately third person throughout.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions and metrics — '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' — giving comprehensive coverage of what the skill produces.	5 / 5
Completeness	Explicitly answers both what ('Generate a Progress Tracker HTML ... Uses Plans.md as source of truth') and when ('Use when user asks for progress overview ...') plus an explicit negative trigger ('Do NOT load for: actual implementation, code review, release work').	5 / 5
Trigger Term Quality	Comprehensive natural trigger terms including English phrases ('progress overview', 'session status snapshot', 'dashboard', 'progress tracker') and Japanese synonyms ('進捗確認', '進捗ボード'), matching the 'including synonyms' anchor.	5 / 5
Distinctiveness Conflict Risk	Clear niche (session progress dashboard for non-engineer vibecoders) with distinct triggers and an explicit 'Do NOT load for' boundary that separates it from implementation, review, and release skills.	5 / 5
	Total	20 / 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
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
Path: opencode/skills/harness-progress/SKILL.md
Commit: 2b2b748

Reviewed: 6 days 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.