CtrlK
BlogDocsLog inGet started
Tessl Logo

harness-init

One-time, guided setup of the local agent-first coding harness — the polling loop, the deterministic dispatcher, its config, the AGENTS.md contract, and the worktree provisioning that makes per-feature worktrees runnable. Use when a developer wants to set up, bootstrap, install, or initialize the coding harness for the first time in a project.

74

Quality

92%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Low

Low-risk findings worth noting

The canonical home for this skill is harness-init in tdg-ninja/context-specs-factory-ai

SKILL.md
Quality
Evals
Security

Quality

Content

85%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, multi-step guided setup with strong sequencing, validation checkpoints, and clean progressive disclosure into real reference files. The only slack is minor verbosity in a few rationale passages and a handful of inherently non-copy-paste generation steps.

DimensionReasoningScore

Conciseness

The body is dense and almost entirely domain-specific actionable detail rather than generic concept padding, but a few explanatory passages (e.g., the wrapper-vs-dispatcher sync rationale) could be trimmed slightly; it is noticeably above the midpoint of efficient.

4 / 5

Actionability

It provides concrete, executable commands — 'git worktree add --detach ../<repo>-harness origin/main', '/loop 5m /poll-and-dispatch', 'gh release view --repo anthropics/claude-code-action' — plus explicit file-copy paths, though the Software 3.0 generation steps are inherently scan-and-propose rather than copy-paste.

4 / 5

Workflow Clarity

A clearly sequenced Step 0–10 flow with explicit validation checkpoints (preflight report, confirm→do→show→feedback, 'doubles as validation of the bootstrap script — Fix and re-run if not', 'If anything errors, debug before starting the loops') and feedback loops for destructive/git and batch operations.

5 / 5

Progressive Disclosure

The body is a clear overview that points one level deep to real, well-signaled references (references/*.md, assets/*) and outsources detail to them ('Read references/dispatcher-explained.md'); all referenced paths resolve to actual bundle files.

5 / 5

Total

18

/

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.

A strong, third-person description that names concrete artifacts, supplies natural trigger synonyms, and explicitly pairs a 'what' with a 'when' clause. Minimal conflict risk thanks to the one-time-setup framing.

DimensionReasoningScore

Specificity

The description enumerates multiple concrete artifacts to set up — 'the polling loop, the deterministic dispatcher, its config, the AGENTS.md contract, and the worktree provisioning' — giving comprehensive coverage of concrete actions rather than vague language.

5 / 5

Completeness

It explicitly answers both what (the five named harness components) and when (an explicit 'Use when a developer wants to set up... for the first time in a project' trigger clause with concrete conditions).

5 / 5

Trigger Term Quality

It supplies several natural synonyms a developer would say — 'set up, bootstrap, install, or initialize the coding harness for the first time in a project' — covering the common phrasings users actually invoke.

5 / 5

Distinctiveness Conflict Risk

The 'one-time, guided setup... for the first time in a project' framing carves a clear niche distinct from the runtime harness skills (poll-and-dispatch, learn-loop), minimizing wrong-skill triggering.

5 / 5

Total

20

/

20

Passed

Validation

93%

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

Validation15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

referenced_paths_exist

Referenced path issues: 6 missing, 1 deeper-than-1-level

Warning

Total

15

/

16

Passed

Repository
tdg-ninja/context-specs-claude-code
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.