CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

development

Comprehensive web, mobile, and backend development workflow bundling frontend, backend, full-stack, and mobile development skills for end-to-end application delivery.

Quality

59%

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

Fix and improve this skill with Tessl

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

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

SKILL.md
Quality
Evals
Security

Quality

Content

60%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 well-organized orchestration document: clear phase sequencing, concrete skill routing with @-syntax, and quality-gate checkpoints. Its weaknesses are redundancy (prompts and technology sections restate the skill lists) and high-level action steps with no failure-handling guidance, leaving it at 'good but not excellent' on actionability and conciseness.

Suggestions

Add a feedback loop to the Quality Gates: state what to do when a gate fails (e.g. 'if any gate fails, fix and re-run before proceeding to the next phase') to lift workflow clarity from 4 toward 5.

Cut duplication by either dropping the Copy-Paste Prompts or replacing the per-phase skill lists with them, rather than carrying both; the Technology-Specific Workflows section could likewise reference phase skills instead of relisting them.

Make the numbered Actions concrete — name the specific tool or command per action (e.g. 'Set up version control and CI/CD' → which skill, which template) or explicitly defer to the bundled skill, so guidance is executable rather than descriptive.

DimensionReasoningScore

Conciseness

The body thankfully contains no explanation of concepts Claude already knows and keeps prose minimal, but roughly 90 lines of 'Copy-Paste Prompts' largely restate the per-phase 'Skills to Invoke' lists, and the 'Technology-Specific Workflows' section repeats the same skill names a third time. This is 'mostly efficient but could be tightened' (anchor 3) rather than 4, where duplication would be only minor.

3 / 5

Actionability

As an orchestration skill its guidance is partly concrete — it names exact skills per phase with @-syntax and gives copy-paste invocations like 'Use @app-builder to scaffold a new React + Node.js full-stack application'. However, the numbered 'Actions' in every phase are high-level verbs with no specifics ('Design component architecture', 'Configure middleware', 'Set up version control and CI/CD') — steps are named but the key details of how to execute or evaluate them are missing, matching anchor 3 rather than 4.

3 / 5

Workflow Clarity

The seven phases (setup → frontend → backend → database → testing → review → deployment) are clearly ordered, each with skills, actions, and prompts, and the 'Quality Gates' checklist provides explicit checkpoints between phases. It falls short of anchor 5 because there is no feedback loop — the gates say 'verify' but never say what to do when a gate fails or how to recover — which is exactly the 'minor validation gap' of anchor 4.

4 / 5

Progressive Disclosure

The single file is well-sectioned with a clear header hierarchy (phases, technology workflows, quality gates) making it easy to navigate, and there are no bundle files (references/, scripts/, assets/ are absent) so nothing is misfiled. It is not a 5 because everything lives inline in one ~250-line file — the per-phase and technology-specific detail could be split into one-level-deep reference files — but the structure and placement are good, matching anchor 4.

4 / 5

Total

14

/

20

Passed

Description

41%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 states a clear structural purpose (a workflow bundle orchestrating development skills) but relies on buzzwords and domain labels rather than concrete actions, includes no 'Use when' trigger guidance, and is so broad that it would compete with the very skills it routes to. Adding explicit trigger conditions and replacing 'Comprehensive'/'end-to-end' with concrete capabilities would materially improve it.

Suggestions

Add an explicit 'Use when...' clause, e.g. 'Use when starting a new web/mobile project, adding a feature across frontend and backend, or modernizing a legacy codebase' — its absence currently caps completeness at 3.

Replace buzzword framing ('Comprehensive', 'end-to-end application delivery') with 1-2 concrete actions, e.g. 'Orchestrates skills through setup, frontend, backend, database, testing, review, and deployment phases'.

Narrow the stated scope or add distinguishing trigger phrases so it does not fire on every development request in place of the specific sub-skills it bundles.

DimensionReasoningScore

Specificity

The description names the domains ('web, mobile, and backend development', 'frontend, backend, full-stack, and mobile development skills') but the only actions offered are the generic 'bundling ... skills' and 'end-to-end application delivery' — no concrete action like 'scaffold projects' or 'review pull requests' is stated. It is not a 3 because there is no genuinely concrete action named, and not a 1 because it does state a specific structural function (orchestrating a defined set of development skills).

2 / 5

Completeness

The 'what' is reasonably clear ('workflow bundling frontend, backend, full-stack, and mobile development skills for end-to-end application delivery'), but there is no 'Use when...' clause or any equivalent explicit trigger guidance, capping completeness at 3 per the rubric guidelines. Not a 4 because the 'when' is entirely missing rather than merely imprecise; not a 2 because the 'what' is clearly stated, not vague.

3 / 5

Trigger Term Quality

It includes natural domain keywords a user might say ('web', 'mobile', 'backend', 'frontend', 'full-stack', 'development'), but common trigger phrases users actually use — 'build an app', 'add a feature', 'set up a project', 'deploy' — are absent, and 'Comprehensive' and 'end-to-end' are buzzwords rather than triggers. It sits between anchor 3 (some relevant keywords, missing common variations) and 4, closer to 3 because the keywords are all variations of one word ('development') rather than distinct natural phrases.

3 / 5

Distinctiveness Conflict Risk

The description spans all of software development, which is exactly the territory of the skills it bundles ('app-builder', 'senior-fullstack', 'frontend-developer', 'backend-architect'), creating high overlap risk where any development request could match both this bundle and a specific sub-skill. It is not a 3 because the breadth is extreme rather than 'somewhat specific'; not a 1 because it does describe a distinctive orchestration role rather than being purely generic.

2 / 5

Total

10

/

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.

Validation — 15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

frontmatter_unknown_keys

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

Warning

Total

15

/

16

Passed

Repository

administrakt0r/AI-Agents-Safe-Coding-Skills

Path

plugins/AI-Agents-Safe-Coding-Skills/skills/development/SKILL.md

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.