CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

ecosystem-weaver

Self-improving /loop runbook that weaves the ruvnet package fabric. Each tick ingests lane reports into the weaver ledger, refreshes the package graph, repo scans, open PRs and release checks, ranks a one-lane-per-repo queue, and dispatches up to 8 lanes that integrate, fix, land, create and publish packages behind hard gates. Use for ecosystem cross-integration, release-regression repair, open-PR triage, and autopilot package creation across ruvnet repos.

Quality

91%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Medium

Suggest reviewing before use

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.

An exceptionally actionable, well-sequenced operational runbook: concrete commands, explicit gates with exit codes and override feedback loops, and strong guardrails for batch and destructive operations. The two gaps are minor: dated incident notes and a version anecdote that dilute token efficiency, and a monolithic single-file layout where reference material could be split out.

Suggestions

Move the dated incident rationale (e.g. 'Two over-broad cleanups on 2026-11-05 removed other lanes' work', 'user decision 2026-11-05') into a short 'why' footnote per rule or a background section, so time-sensitive details don't sit in the operational path.

Split the signal-type/kind mapping and the gate-scope details ('Gate scope', 'zero_caret'/'fix_unreachable' semantics) into a references/ file (e.g. references/signals.md) linked from the body, keeping SKILL.md as the tick-time overview.

DimensionReasoningScore

Conciseness

The body is dense and assumes competence with no filler concept explanations, but carries time-stamped incident rationale ("Two over-broad cleanups on 2026-11-05 removed other lanes' work", "user decision 2026-11-05") and a concrete version anecdote ("metaharness ^2.5.6 beat ruvector ^4.1.0") that could be trimmed. Efficient with minor instances that could be tightened, matching level 4 rather than level 5's 'every token earns its place'.

4 / 5

Actionability

Fully executable throughout: exact commands like "$W queue --gate-top 20", "$W ledger record --repo R --candidate C --subject S --kind K --signal SK --outcome in_progress", "$W vuln-evidence X --dir <consumer> --affected \"<range>\"", the gcloud token retrieval, and jq queries for reading queue.json. Copy-paste ready and covering the common cases.

5 / 5

Workflow Clarity

"The tick (run in this order)" gives a numbered sequence with explicit checkpoints (record in_progress "so the repo stays busy and no later tick double-dispatches it"), validation feedback loops (gate "refuses (exit 2)... unless the ledger holds --outcome override", "weaver readme --lint README.md must pass", vuln-evidence "exits 2 when none falls inside the affected range"), and a hard-rules checklist. The batch/destructive operations all have validation, so no cap applies; only the odd '0.' step between 3 and 4 keeps it from being flawless, but it is explicitly labeled 'Run direct items first'.

5 / 5

Progressive Disclosure

No bundle files exist, so everything lives in a single well-sectioned file (Setup, The tick, Hard rules, Reading the queue) with no nested or buried references. Good structure and placement, but at ~155 dense lines the signal-type mapping and gate-scope details are candidates for a references/ split, so it falls short of level 5's 'content appropriately split'.

4 / 5

Total

18

/

20

Passed

Description

92%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: concrete, comprehensive action coverage with an explicit 'Use for' trigger clause and a clearly pinned niche. The only weaknesses are jargon-heavy phrasing ('weaves the ruvnet package fabric') and a lack of synonym-level trigger terms.

DimensionReasoningScore

Specificity

The description enumerates the full tick concretely: "ingests lane reports into the weaver ledger, refreshes the package graph, repo scans, open PRs and release checks, ranks a one-lane-per-repo queue, and dispatches up to 8 lanes that integrate, fix, land, create and publish packages". Coverage is comprehensive with only the opening "weaves the ruvnet package fabric" clause being vague, which is not enough to drop to level 4's 'minor gaps'.

5 / 5

Completeness

It explicitly answers both questions: what ("Each tick ingests lane reports... ranks a one-lane-per-repo queue, and dispatches up to 8 lanes...") and when ("Use for ecosystem cross-integration, release-regression repair, open-PR triage, and autopilot package creation across ruvnet repos"). This matches the level-5 anchor of both what and when with concrete trigger phrases.

5 / 5

Trigger Term Quality

"Use for ecosystem cross-integration, release-regression repair, open-PR triage, and autopilot package creation" gives good natural trigger phrases, but the description leans on internal jargon ("package fabric", "lanes", "weaver ledger") and offers no synonyms or extensions (e.g. npm publish, CI, regression fix). Not comprehensive enough for 5, but well above 'some relevant keywords' (3).

4 / 5

Distinctiveness Conflict Risk

"across ruvnet repos" and the specific triggers (release-regression repair, open-PR triage, autopilot package creation) carve out a clear niche with minimal overlap risk against generic loop or ecosystem skills.

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

frontmatter_unknown_keys

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

Warning

Total

15

/

16

Passed

Repository

ruvnet/RuVector

Path

.claude/skills/ecosystem-weaver/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.