sweep-labs
Identifies and manages orphan artifacts within the labs ecosystem with a human-confirmation gate.
Install
mkdir -p .claude/skills/sweep-labs && curl -L -o skill.zip "https://agentskills.codes/api/skills/download/11403" && unzip -o skill.zip -d .claude/skills/sweep-labs && rm skill.zipInstalls to .claude/skills/sweep-labs
Activation
This is the description your AI agent reads to decide when to run this skill — the better it matches your request, the more reliably it fires.
Diff connect-labs workflows/pipelines/synthetic/solicitations against the live-set, score orphans, auto-delete/disable. Funds and standalone reviews/responses remain report-only (no upstream per-type atom yet).Key capabilities
- →Diff connect-labs artifacts against the live-set
- →Score orphan workflows, pipelines, synthetic opportunities, and solicitations
- →Generate human-readable and machine-readable orphan reports
- →Delete approved orphan workflows and pipelines
- →Disable approved orphan synthetic opportunities
- →Delete approved orphan solicitations
How it works
The skill reads a live-set file, lists labs inventory, and then diffs the inventory against the live-set's labs buckets. It scores each orphan and builds an OrphanReport.
Inputs & outputs
When to use sweep-labs
- →Cleanup orphan workflows
- →Audit labs artifacts
- →Disable unused pipelines
About this skill
sweep-labs
Find connect-labs artifacts (workflows, pipelines, synthetic opportunities, solicitations, funds, reviews, responses) that no current opp references. Workflows, pipelines, synthetic opps, and solicitations have first-class delete/disable atoms in the labs MCP — deletable in the execute pass, after the orchestrator's per-system human-confirmation gate (see agents/sweep.md § Human-confirmation gate). The remaining LabsRecord-backed types (funds + standalone reviews/responses) are report-only by design until per-type atoms exist upstream. Reviews and responses cascade-delete with their parent solicitation, so they generally don't need standalone cleanup.
Inputs
- Live-set file path from
sweep-live-set. LABS_MCP_TOKENand labs base URL (loaded viaconnect-labsMCP).- Labs admin base URL:
https://labs.connect.dimagi.com. mode—recommend(default) |execute. Inrecommendthe skill is report-only: diff/score/render + return the recommended-action list; no mutations (no delete/disable). Inexecuteit mutates onlyapprovedIds. The human-confirmation gate between the two is the orchestrator's job — seeagents/sweep.md § Human-confirmation gate.approvedIds(executemode only) — the exact workflow/pipeline/synthetic/solicitation/update-link/quote ids the human approved in chat. Mutate nothing outside this set. Aforce: truedelete of a solicitation with seeded responses is approved per solicitation, by name, never by a blanket approval.programIds(optional explicit argument) — labs program ids to audit for supply-chain records. Default: everyprogram_idon a solicitation ACE's orgs own (Step 2), plus everyphases.execution-management.products.supply_chain.program_idthe live-set's runs carry.
Products
ACE/_sweep/<timestamp>/labs-orphans.md— human-readable triage report.ACE/_sweep/<timestamp>/labs-orphans.yaml— machine-readableOrphanReport.- For approved orphan workflows:
workflow_deletecalls. - For approved orphan pipelines:
pipeline_deletecalls. - For approved orphan synthetic opps:
synthetic_disablecalls. - For approved orphan solicitations:
delete_solicitationcalls (cascade-deletes reviews + responses; gated on cascade emptiness — connect-labs PR #197). - For approved supply-chain items:
supply_chain_update_link_revokeandsupply_chain_quote_voidcalls. - An irreversible-records section in
labs-orphans.md: the supply-chain records labs keeps no delete for, listed for audit (§ "Optional labs track" below).
Process
- Read the live-set via
drive_read_file. - List labs inventory using existing atoms:
workflow_listpipeline_listlist_solicitations(each entry includesprogram_id,statusandis_public). It returns every call ACE's organisations own, unlisted (is_public: false) ones included, plus every public call. Noprogram_idis needed to see an unlisted call you own — that was a stale claim, refuted against the live schema in #3166. Passorganization_idper ACE org (pm_org,nm_org,llo_org) to scope the listing to ACE's own calls.list_fundslist_reviewslist_responses
- Diff against the live-set's labs buckets:
- workflows →
liveSet.identifiers.labsWorkflowIds - pipelines →
liveSet.identifiers.labsPipelineIds - synthetic opps →
liveSet.identifiers.labsSyntheticIds - solicitations/funds/reviews/responses →
liveSet.identifiers.labsRecordIds
- workflows →
- Score each orphan via
scoreLabsItem(item, liveSet)fromlib/sweep-fingerprint.ts. Pass each item'snameAND itsdescription(workflows, registries, cohorts) /notes(synthetic opps): a Phase 7 object carries its sweep handle(synthetic, ace <opp>/<run-id>)in whichever field no frame renders — a rendered object (programme report, opp report, synthetic opportunity) has it indescription/notes, never its name (demo-data-setup§ C7 "Sweep handles", ace#2733).sweepHandleFieldchecks all three and the score names the field and the run it came from. The scorer defensively downgrades tolowwhen an item references a Connect opportunity that's still inliveSet.identifiers.connectOpportunityIds— that's a sign the caller mis-flagged the item. - Build the
OrphanReportwithsystem: 'labs'. Partition into:- Actionable (deleted in the execute pass, after human approval): workflows, pipelines, synthetic opps, orphan solicitations. Solicitation deletion is gated on
responses + reviews == 0(cascade emptiness), not on lifecycle status — every ACE dogfood solicitation passes that gate cleanly because no real LLO ever engaged. See connect-labs PR #197. - Informational only: funds, standalone reviews/responses (reviews+responses that were already cascade-deleted with a parent solicitation don't appear here). Funds may need their own per-type atom in a future labs MCP release; reviews/responses generally cascade with their parent solicitation.
- Supply-chain items (optional labs track): active update links, and quotes that are neither awarded nor voided, in a program that is orphaned or whose run has closed — see § Optional labs track.
- Actionable (deleted in the execute pass, after human approval): workflows, pipelines, synthetic opps, orphan solicitations. Solicitation deletion is gated on
- Render + write
labs-orphans.mdand.yamlto the sweep folder, including the irreversible-records section. - Recommend — stop here in
mode: recommend. Return the structured recommended-action list (orphan workflows/pipelines/synthetic to delete-or-disable; orphan solicitations to delete with their cascade preview — each with id, confidence) plus the informational-only items (funds, standalone reviews/responses) and the report Drive link, to the orchestrator. Perform no mutations. Do not try to prompt the human from this skill — a dispatched subagent can't reach them; the orchestrator runs the confirmation gate (seeagents/sweep.md § Human-confirmation gate).
Execute phase (mode: execute only)
Runs only when the orchestrator re-dispatches with mode: execute + approvedIds (the ids the human approved in chat). Mutate only those ids:
-
Orphan workflows →
workflow_delete({ workflow_id }) -
Orphan pipelines →
pipeline_delete({ pipeline_id }) -
Orphan synthetic opps →
synthetic_disable({ synthetic_opp_id }) -
Orphan solicitations →
delete_solicitation({ solicitation_id })(program_idis "accepted for compatibility; not needed" in the live schema). The atom cascade-deletes the solicitation's reviews and responses in one call and returns the count of records deleted at each level — surface that in the result so the human sees the cascade impact. Passforce: trueonly for the rare legitimate destroy-with-engagement-data case (test fixtures that intentionally include responses) — and only if the human explicitly approved that override. -
Approved update links →
supply_chain_update_link_revoke({ program_id, link_id, source: { ref: "ace:sweep:<timestamp>:update-link:<link_id>" } }). It stops working at once and cannot be re-enabled; what was recorded through it stays. -
Approved quotes →
supply_chain_quote_void({ program_id, quote_id, reason: "ACE sweep <timestamp>: simulated run <run-id> closed", source: { ref: "ace:sweep:<timestamp>:quote:<quote_id>" } }). The quote stays readable and drops out of comparisons.
Funds, standalone reviews/responses and every irreversible supply-chain record are never mutated (report-only). Return the per-item result.
Optional labs track (--with labs_e2e runs)
A run with the optional steps on (spec docs/superpowers/specs/2026-10-18-optional-labs-e2e-steps.md) leaves three kinds of labs objects behind, each with a different cleanup:
- Private solicitations with seeded responses.
solicitation-seed-responsesfiles fictional respondents (names end[Synthetic], the run's roster lists them). Because the call then HAS responses,delete_solicitationrefuses it withoutforce: true. Recommend it as a per-solicitationforcedelete, with the cascade preview, and say the responses are ACE-seeded fixtures. The human approves the override for that solicitation by name. A solicitation with any response NOT on the run's seeded roster is real engagement data: report it, never recommendforce. - Removable supply-chain items. For each program in
programIds:supply_chain_update_link_list({ program_id, include_inactive: false })→ recommend revoking every active link of an orphaned or closed run;supply_chain_quote_list({ program_id })→ recommend voiding every quote that is neither awarded nor already voided, on a tender no live run still has open. These are the only supply-chain removals labs offers. - Irreversible records — report, never act. Labs keeps no delete for tenders, quotes, awards, contracts, shipments, consignments, receipts, invoices, payments, stock counts or distributions (spec § F6), and a declared programme runner can only be changed by that runner's admins or support, never removed. For each program, list counts from the matching
supply_chain_*_listreads andsupply_chain_programme_runner_get, each with the run that wrote it. The isolation for these is the program itself: they are scoped to ACE's own program, named "simulated", and stay there for audit.
Known ACE-made items as of 2026-10-18, so the first sweep after them reads them right rather than flagging them as strays:
- Private call 1000003 on program 308 (owned by
connect_orgs.pm_org), closed, with seeded responses 1000046–1000049: the PR4 live probe (#3176). Deletable: recommendforce: truewith the cascade preview. - Program 308's runner declaration (
connect_orgs.pm_org's labs org, 352): the live check of connect-labs #2605. Irreversible from ACE; report it. Nothing else was written to program 308's supply chain.
Failure modes
- Live-set path doesn't resolve: abort with "Run
sweep-live-setfirst." - Labs MCP returns 401:
LABS_MCP_TOKENis expired; recommend `/
Content truncated.
When not to use it
- →When funds require mutation
- →When standalone reviews or responses require mutation
- →When per-type atoms for funds are not yet available upstream
Limitations
- →Funds remain report-only
- →Standalone reviews and responses remain report-only
- →Solicitation deletion is gated on cascade emptiness
How it compares
This skill automates the identification, scoring, and deletion/disabling of unused labs artifacts, which would otherwise require manual inventory checks and individual deletions.
Compared to similar skills
sweep-labs side by side with the closest alternatives in the catalog.
| Skill | Installs | Updated | Safety | Difficulty |
|---|---|---|---|---|
| sweep-labs (this skill) | 0 | 5mo | No flags | Intermediate |
| applescript | 28 | 12mo | Review | Advanced |
| bazel-build-optimization | 14 | 6mo | No flags | Advanced |
| home-assistant-manager | 9 | 11mo | Review | Advanced |
Try saying
Example prompts that trigger this skill in your AI assistant.
You might also like
applescript
martinholovsky
Expert in AppleScript and JavaScript for Automation (JXA) for macOS system scripting. Specializes in secure script execution, application automation, and system integration. HIGH-RISK skill due to shell command execution and system-wide control capabilities.
bazel-build-optimization
wshobson
Optimize Bazel builds for large-scale monorepos. Use when configuring Bazel, implementing remote execution, or optimizing build performance for enterprise codebases.
home-assistant-manager
komal-SkyNET
Expert-level Home Assistant configuration management with efficient deployment workflows (git and rapid scp iteration), remote CLI access via SSH and hass-cli, automation verification protocols, log analysis, reload vs restart optimization, and comprehensive Lovelace dashboard management for tablet-optimized UIs. Includes template patterns, card types, debugging strategies, and real-world examples.
swarm-advanced
ruvnet
Advanced swarm orchestration patterns for research, development, testing, and complex distributed workflows
windows-expert
jackspace
Expert guidance for Windows, PowerShell, WSL interop, and cross-platform development
bash-linux
davila7
Bash/Linux terminal patterns. Critical commands, piping, error handling, scripting. Use when working on macOS or Linux systems.