CtrlK
BlogDocsLog inGet started
Tessl Logo

bootstrap

Create, diagnose, and validate a local dev bootstrap. Use when the user asks to clone a repo, install toolchains, install dependencies, and prove the project runs.

65

Quality

79%

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 ./Skills/agent-ops/bootstrap/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

70%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 a lean, well-organized contract with a strong validation feedback loop in its workflow. Its weaknesses are abstract, non-executable actionability and a Progressive Disclosure pointer that targets a path not present in the actual bundle.

Suggestions

Point the Progressive Disclosure section at the real bundle location (`./references/` with contract.yaml, evals.yaml, task-profile.json) instead of the non-existent `Infrastructure/references/deferred-skill-context/agent-ops-bootstrap/` path.

Add at least one concrete example command per workflow step (e.g., a representative clone/install/validate command) to lift actionability above directional guidance.

Remove the verbatim restatement of the description on line 10 to eliminate redundancy with the frontmatter.

DimensionReasoningScore

Conciseness

The body is lean and assumes competence throughout, but line 10 restates the frontmatter description verbatim and the Examples restate trigger phrasing — minor redundancy that could be trimmed, so below the 5 anchor.

4 / 5

Actionability

Guidance is directional ("Inspect 2-3 focused surfaces", "Take the smallest action that advances the confirmed goal") with no concrete commands or executable steps; as an instruction-only skill the Inputs/Outputs lists add some concreteness, but key execution detail is missing.

3 / 5

Workflow Clarity

A clear 5-step sequence with explicit validation checkpoints — step 4 "Stop at the first failed gate", step 5 "Rerun the relevant validation after fixes" — plus a fail-fast Validation section, matching the feedback-loop anchor.

5 / 5

Progressive Disclosure

The SKILL.md is well-sectioned and the Progressive Disclosure section signals one-level-deep deferred content, but it points to `Infrastructure/references/deferred-skill-context/agent-ops-bootstrap/` while the actual bundle files (contract.yaml, evals.yaml, task-profile.json) sit in `./references/` — the referenced path does not match the real bundle, so navigation is broken.

3 / 5

Total

15

/

20

Passed

Description

88%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 description that clearly states capabilities and explicit, natural trigger conditions. It is comprehensive on completeness and specificity, with only minor gaps in trigger synonyms and distinctiveness against generic setup skills.

DimensionReasoningScore

Specificity

Names the domain and lists multiple concrete actions — "clone a repo, install toolchains, install dependencies, and prove the project runs" — giving comprehensive coverage; not below 5 since the action set is broad and specific, not a partial list.

5 / 5

Completeness

Explicitly answers both "what" ("Create, diagnose, and validate a local dev bootstrap") and "when" ("Use when the user asks to clone a repo...") with concrete trigger phrases, matching the 5 anchor.

5 / 5

Trigger Term Quality

Natural user phrases like "clone a repo", "install dependencies", and "prove the project runs" give good coverage, but synonyms and file/extension variants are absent, so it falls short of the comprehensive 5 anchor.

4 / 5

Distinctiveness Conflict Risk

The bootstrap niche with triggers like "install toolchains" and "prove the project runs" is mostly distinct, but "clone a repo / install dependencies" overlaps with general dev-setup skills, keeping it just below the 5 anchor.

4 / 5

Total

18

/

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

metadata_version

'metadata.version' is missing

Warning

Total

15

/

16

Passed

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.