CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

dia-setup

Activates, reconfigures, or deactivates the Digital Innovation Agents workflow in a project. Writes the .dia/config.toml settings file and manages anchor blocks in agent-facing files (CLAUDE.md, AGENTS.md, GEMINI.md, .cursorrules, .github/copilot-instructions.md, .windsurfrules). Use this skill when the user mentions "DIA aktivieren", "DIA installieren", "DIA initialisieren", "DIA setup", "DIA settings", "Workflow-Modus", "Modus wechseln", "DIA off", "DIA deaktivieren", "Plugin aktivieren". Single skill that covers both first-time activation and later reconfiguration; the skill detects which path applies from the presence of .dia/config.toml.

Quality

92%

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

SKILL.md
Quality
Evals
Security

Quality

Content

88%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-engineered operational skill document: exact commands, explicit validation and idempotency guarantees, and well-branching error handling for the gh pre-flight. The main improvements are removing the duplicated [github]/project-number explanations between the activation flow and the settings-format section, and turning the reference pointer into a clearly signaled link.

Suggestions

Deduplicate the [github] field semantics: activation step 4 and the 'Settings file format' section both explain project_number/status_field/project_owner and repeat the identical 'the issue itself still syncs, only the project Status field stays untouched' sentence — state the field semantics once and cross-reference from the flow.

Merge the 'Hand-off' section into the intro or the confirmation step, since it restates scope boundaries already declared at the top ('does not run any phase skill... does not invoke flow.py').

Signal the reference more clearly as a link to the bundled file (e.g. 'See [references/anchor-format.md](references/anchor-format.md)') instead of a bare repo-relative code path, so the pointer is unambiguous from the SKILL.md location.

DimensionReasoningScore

Conciseness

The body is dense and operational with no concept explanations Claude already knows, but contains real duplication: 'the issue itself still syncs, only the project Status field stays untouched' appears verbatim in both activation step 4 and the settings-format section, the [github] field semantics are explained twice, and the 'Hand-off' section restates the intro's scope boundaries ('does not invoke any phase skill... does not start any handoff ritual'). This fits the level-4 anchor (efficient with minor trimming opportunities) rather than level 5.

4 / 5

Actionability

Guidance is copy-paste executable throughout: exact commands ('gh project view <N> --owner <owner> --format json', 'python3 tools/dia-setup/anchor.py write --mode <mode> --files <selected list>', 'gh auth refresh -s project'), a concrete template path with named placeholders ({{mode}}, {{anchor_files}}, source_branch), a full example config.toml, and specific AskUserQuestion option structures. Error-recovery branches for the gh pre-flight (missing scope vs wrong number vs other owner) cover the realistic failure cases, matching the level-5 anchor.

5 / 5

Workflow Clarity

Two flows are cleanly separated by a single routing check ('does .dia/config.toml already exist?'), each with numbered, sequenced steps, and the skill has an explicit post-write validation loop ('the skill calls python3 tools/dia-setup/anchor.py verify and reports the result... surface the missing files to the user and offer a refresh') plus a documented idempotency guarantee. Destructive-adjacent operations (anchor block rewrite, deactivation removing blocks) are covered by verify and remove semantics, so the missing-validation cap does not apply — this matches the level-5 anchor with explicit checkpoints and feedback loops.

5 / 5

Progressive Disclosure

The split is appropriate: the body holds the setup workflow while anchor-block format and idempotency internals live in references/anchor-format.md (verified to exist, one level deep, well sectioned, no nested references). However, the pointer is given as a bare code path ('skills/dia-setup/references/anchor-format.md') rather than a clearly signaled markdown link to the bundled reference, and the settings-format TOML example arguably duplicates content that could be consolidated. This fits the level-4 anchor (good structure, references mostly clear, minor organization gaps) more than level 5.

4 / 5

Total

18

/

20

Passed

Description

95%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 pairs concrete capabilities with an unusually thorough bilingual trigger list and explicit what/when coverage. The only soft spot is the slightly generic 'manages anchor blocks' phrasing, which compresses several concrete operations into one vague verb.

DimensionReasoningScore

Specificity

The description lists several concrete actions ('Activates, reconfigures, or deactivates', 'Writes the .dia/config.toml settings file') and names the exact agent-facing files anchor blocks apply to, but 'manages anchor blocks' is a generic verb wrapping the underlying write/replace/remove operations — a minor coverage gap versus the fully atomic action lists of the level-5 anchor. It is clearly above the level-3 anchor (which expects only 1-2 concrete actions).

4 / 5

Completeness

It explicitly answers what the skill does (activate/reconfigure/deactivate, write .dia/config.toml, manage anchor blocks in named files) and when to use it ('Use this skill when the user mentions...' followed by concrete trigger phrases), plus routing detail ('the skill detects which path applies from the presence of .dia/config.toml'). This is a direct match for the level-5 anchor.

5 / 5

Trigger Term Quality

Ten natural trigger phrases users would actually say are enumerated ('DIA aktivieren', 'DIA installieren', 'DIA initialisieren', 'DIA setup', 'DIA settings', 'Workflow-Modus', 'Modus wechseln', 'DIA off', 'DIA deaktivieren', 'Plugin aktivieren'), covering synonyms across German and English as well as file artifacts (.dia/config.toml). This matches the level-5 anchor's comprehensive synonym coverage; the level-4 anchor is reserved for lists with notable missing natural terms.

5 / 5

Distinctiveness Conflict Risk

The description occupies a clear niche (DIA plugin setup/configuration) with triggers specific to that plugin ('DIA aktivieren', 'Workflow-Modus', 'Modus wechseln') and no plausible overlap with generic setup, git, or documentation skills. Minimal conflict risk, matching the level-5 anchor.

5 / 5

Total

19

/

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

referenced_paths_exist

Referenced path issues: 1 missing

Warning

Total

15

/

16

Passed

Repository

salemaziel/digital-innovation-agents

Path

skills/dia-setup/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.