CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

multica-platform

Use for Multica platform actions the runtime brief does not fully cover: issue and PR contracts, charts and files in comments, mentions, agents, squads, autopilots, projects, runtimes, skill import. Not for the product code you are working on.

68

Quality

85%

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

78%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 overview skill: a domain routing table that matches the real bundle exactly, one-level-deep self-contained references, terse invariants with concrete flags and failure modes, and explicit safety checkpoints (read before write, writes are real, don't merge stderr). The residual gaps are minor: a few trimmable rhetorical phrases and inline command fragments that omit the command verb itself.

DimensionReasoningScore

Conciseness

The body is dense and disciplined — a routing table plus terse invariants, no explanations of concepts Claude already knows, and explicit anti-read-all guidance ("What is never right is reading all eight because you are not sure"). A few rhetorical flourishes ("an exception… narrower than it looks", the long comment-reads exception paragraph) could be trimmed, matching anchor 4 rather than a fully lean 5.

4 / 5

Actionability

Concrete commands and flags throughout: `multica <command> --help`, `--output json`, `--roots-only --summary --compact`, `--thread <thread-id> --tail 30`, `--since`, `--*-id`, plus concrete failure modes (a `2>&1` merge makes a successful write look failed and invites a duplicate retry). Full command verbs per domain are deferred to the references — a minor gap that is deliberate but leaves the inline fragments not quite copy-paste ready.

4 / 5

Workflow Clarity

A clear sequenced workflow with explicit validation checkpoints: read the routing table, open only the needed reference, run read-only `list`/`get` with `--output json` before any mutation, and never run a write speculatively ("Never run one to see what happens"). Error-recovery guidance exists (don't merge stderr, misdiagnosed well-formed-but-wrong UUIDs, classify before concluding), but there is no single numbered checklist — per-domain procedures live in the references, so minor validation gaps remain at this level.

4 / 5

Progressive Disclosure

The routing table maps eight task domains to exactly the eight files that exist in references/ (verified against the actual bundle), each with a one-line "when to open" signal. References are one level deep (siblings in a single directory, no nesting), the body states they are self-contained, and it explicitly instructs selective reading — a clear, well-signaled, easily navigable overview matching anchor 5.

5 / 5

Total

17

/

20

Passed

Description

87%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: it names a distinct platform niche, enumerates the domains it covers, provides an explicit "Use for…" trigger, and closes with a clear exclusion clause. The main limitation is that the capability list is topic nouns ("issue and PR contracts") rather than concrete verb actions, which slightly blunts specificity and trigger-term coverage.

DimensionReasoningScore

Specificity

Enumerates concrete domains ("issue and PR contracts, charts and files in comments, mentions, agents, squads, autopilots, projects, runtimes, skill import") with comprehensive coverage, but these are topic nouns rather than verb-phrase actions. Anchor 4 ("lists several specific actions; minor gaps") fits better than anchor 5's action-rich examples.

4 / 5

Completeness

Explicitly answers both what ("Multica platform actions the runtime brief does not fully cover", followed by a concrete domain list) and when ("Use for…" trigger phrase plus the explicit exclusion "Not for the product code you are working on"). This matches the anchor-5 pattern of concrete trigger phrases with a clear negative boundary.

5 / 5

Trigger Term Quality

Natural platform terms users would say are present: "Multica platform", "mentions", "agents", "squads", "autopilots", "skill import", "projects", "runtimes". A few natural variations covered in the references ("webhook", "daemon", "worktree", "leader routing") are missing from the description.

4 / 5

Distinctiveness Conflict Risk

A clearly bounded niche: the distinctive platform name "Multica", explicit scoping against the runtime brief, and an explicit non-goal (product code) minimize overlap with other skills.

5 / 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.

Validation — 15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

allowed_tools_field

'allowed-tools' contains unusual tool name(s)

Warning

Total

15

/

16

Passed

Repository

multica-ai/multica

Path

server/internal/service/builtin_skills/multica-platform/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.