CtrlK
BlogDocsLog inGet started
Tessl Logo

build

build

49

Quality

55%

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

Fix and improve this skill with Tessl

tessl review fix ./plugins/AI-Agents-Safe-Coding-Skills/skills/build/SKILL.md

The canonical home for this skill is build in administrakt0r/AI-Agents-Safe-Coding-Skills

SKILL.md
Quality
Evals
Security

Quality

Content

57%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 content is a thorough, actionable workflow with concrete file paths, prompt configs, and output templates, but it is monolithic and padded with repetition across subcommands. Destructive overwrite operations lack validation feedback loops, capping workflow clarity.

Suggestions

Extract the RESEARCH.md/IMPLEMENTATION.md/PROGRESS.md markdown templates into reference files (e.g. templates/) and link to them, reducing the inline bulk.

Add a validation/backup checkpoint before destructive Overwrite operations (e.g. back up the existing doc, confirm content is captured) to enable a feedback loop.

De-duplicate the repeated 'get feature name' and 'verify doc exists' steps by referencing a shared procedure instead of restating full AskUserQuestion blocks per subcommand.

DimensionReasoningScore

Conciseness

The body is actionable but noticeably padded: the get-feature-name and verify-doc-exists steps are repeated verbatim across five subcommands, and full AskUserQuestion option blocks plus ~40-line markdown templates are inlined; matches 'mostly efficient but includes some unnecessary explanation or could be tightened'; not a 2 because the material is procedural rather than conceptual fluff.

3 / 5

Actionability

Provides concrete routing, explicit file paths (docs/{name}/RESEARCH.md), fully specified AskUserQuestion configs with exact questions/headers/options, and complete output-document templates; matches 'mostly executable guidance with minor gaps'; not a 5 because the research/implementation steps rely on high-level directives ('conduct DEEP research') rather than copy-paste-ready specifics.

4 / 5

Workflow Clarity

Subcommand steps are clearly numbered and include doc-existence checkpoints, but the Overwrite operations on existing RESEARCH/IMPLEMENTATION/PROGRESS docs are destructive with no validate-before-overwrite or backup feedback loop, so per the destructive-operations cap workflow clarity cannot exceed 3; not a 2 because sequencing and existence checks are present.

3 / 5

Progressive Disclosure

The skill is well-organized into subcommand sections and numbered steps, but it is monolithic (~630 lines) with large inlined markdown templates and AskUserQuestion configs that belong in separate reference files, and no bundle files exist; matches 'some structure but content that should be separate is inline'; not a 4 because no external references split the bulk out.

3 / 5

Total

13

/

20

Passed

Description

53%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 clearly states what the skill does but omits any explicit 'when to use' trigger guidance, which caps its completeness. Trigger terms are relevant but lack the natural phrasing users would actually say.

Suggestions

Add an explicit 'Use when...' clause, e.g. 'Use when the user wants to plan and build a major feature end-to-end.'

Include natural user-facing trigger phrases such as 'build a feature', 'add a feature', or 'plan a feature'.

Make the actions more concrete (e.g. 'research, phased implementation plans, progress tracking, and step-by-step implementation') instead of generic verbs.

DimensionReasoningScore

Specificity

Names the domain ('feature development pipeline') and four actions ('research, plan, track, and implement') but the actions are generic pipeline verbs rather than concrete operations, matching the 'names domain and 1-2 concrete actions, not comprehensive' anchor; not a 4 because the verbs are abstract and not a 2 because it does enumerate multiple actions.

3 / 5

Completeness

Provides a clear 'what' ('Feature development pipeline - research, plan, track, and implement major features') but no 'Use when...' or equivalent explicit 'when' clause, so per the missing-trigger-guidance cap it cannot exceed 3; not a 2 because the 'what' is clear rather than vague.

3 / 5

Trigger Term Quality

Contains relevant keywords like 'feature development', 'research', 'plan', 'implement', and 'major features' but misses the natural phrases a user would actually say ('build a feature', 'add a feature'), fitting 'some relevant keywords but missing common variations'; not a 4 due to absent natural trigger phrasing.

3 / 5

Distinctiveness Conflict Risk

'Feature development pipeline' is a fairly distinct niche with minor overlap risk against generic plan/build skills, matching 'mostly distinct; minor overlap risk with closely related skills'; not a 5 because the verbs (research/plan/implement) overlap with general coding-planning skills.

4 / 5

Total

13

/

20

Passed

Validation

81%

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

Validation13 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

skill_md_line_count

SKILL.md is long (645 lines); consider splitting into references/ and linking

Warning

description_field

'description' is very short (5 chars), consider making it more detailed

Warning

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

Total

13

/

16

Passed

Repository
administrakt0r/AI-Agents-Safe-Coding-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.