Menu
Skills dans ce dépôt
SkillsMP a collecté 3 441 skills depuis vamseeachanta/workspace-hub. Ouvrez un skill pour examiner sa source et ses détails.
vamseeachanta/workspace-hubAffichage de 40 skills collectés sur 3 441.
Build and maintain cross-provider session-log audits for Claude, Codex, Hermes, and Gemini, including exporter design, normalization, and behavioral verification.
Langue du texte source : anglais
Evaluate all workspace-hub skills for structural validity, content quality, cross-reference integrity, and registry consistency. Runs 18 checks across critical, warning, and info severity levels with actionable fix suggestions.
Langue du texte source : anglais
Verify proposed copy changes to vamseeachanta/aceengineer-website against canonical sources in workspace-hub (llm-wiki, live site, strategy repo) before shipping. Produces a GitHub issue on the site repo documenting the check with a Match / Drift / Gap…
Langue du texte source : anglais
Launch approved GitHub issue implementation in parallel using isolated git worktrees, committed execution-pack prompts, local plan-approved markers, and direct background Claude runs when delegate_task workers are unreliable for real repo writes.
Langue du texte source : anglais
Recover an overnight multi-worktree planning wave when some Claude lanes hit quota by relaunching only the failed lanes with Codex in the same isolated worktrees and prompt files.
Langue du texte source : anglais
Handle large pre-plan-review planning waves that succeed analytically but fail to persist artifacts due to quota exhaustion, sandbox write failures, or cancelled GitHub mutations.
Langue du texte source : anglais
Reconcile overnight planning waves where Claude workers advance GitHub issue state but the expected plan/review artifacts are missing from the designated external worktree because the worker wrote from a sandbox/in-repo worktree and pushed directly to the…
Langue du texte source : anglais
Reconcile overnight planning waves when Claude workers move GitHub issues to status:plan-review but local artifacts are missing, split across sandbox worktrees, or only present on a pushed remote branch.
Langue du texte source : anglais
Recover when unattended overnight Claude planning runs exit 0 but produce no required artifacts; salvage the wave by auditing existing plan state, generating missing summary artifacts manually, and preserving morning monitoring surfaces.
Langue du texte source : anglais
Run overnight planning-only waves for issues before status:plan-review, and reconcile cases where GitHub state advances but plan/review artifacts land in a sandbox or remote branch instead of the active local worktree.
Langue du texte source : anglais
Prevent false stalls and missing-log failures in overnight Claude worktree batches by pre-warming uv environments, using exact log-path directory creation, and interpreting buffered logs correctly.
Langue du texte source : anglais
Verify a parked GitHub issue plan-review handoff across live labels, local markers, README rows, canonical review artifacts, and stale plan-body evidence before reporting next action.
Langue du texte source : anglais
Launch and verify a 10-agent planning-only wave that moves open GitHub issues into status:plan-review using one isolated worktree per issue, wave-specific continuation cron, and post-run artifact-reconciliation checks.
Langue du texte source : anglais
Prevent deleted workflow/path references from creeping back into live docs by combining strict scans, legacy allowlists, and shared regex helpers.
Langue du texte source : anglais
Analyze orchestrator session JSONL logs across Claude/Hermes/Codex to produce cross-agent baselines, tool/file frequency analysis, and skill gap detection. Use when auditing agent activity patterns or identifying skill gaps from session data.
Langue du texte source : anglais
Draft multiple follow-up GitHub issue plans in parallel using isolated git worktrees plus background Claude Code print-mode runs, while keeping governance-safe boundaries and avoiding shared-file contention.
Langue du texte source : anglais
Review external LinkedIn posts and fold reusable insights into ACE-style GTM docs, capability maps, and content calendars.
Langue du texte source : anglais
Run an approval-stage adversarial cross-review sweep across multiple GitHub issues, drafting any missing canonical plan artifacts before dispatching Codex/Gemini reviews.
Langue du texte source : anglais
Convert external GTM signals (LinkedIn posts, competitor messaging, market themes) into engineering-first ACE artifacts before drafting marketing copy.
Langue du texte source : anglais
Execute approved GitHub issues in isolated worktrees with interactive Claude Code/Codex runs, while containing agent drift and salvaging progress when provider/runtime problems occur.
Langue du texte source : anglais
Keep iterative plan-review reruns truthful by syncing prompt files, canonical review artifacts, and the plan's own review-summary narrative after each adversarial wave.
Langue du texte source : anglais
Run a planning-only multi-terminal wave to harden blocked `status:plan-review` issues for fresh adversarial re-review, with zero implementation work and explicit path ownership.
Langue du texte source : anglais
Harden a documentation/contract plan before adversarial review by mapping every issue-scope requirement to independent acceptance criteria and tests, especially for routing/indexing contracts.
Langue du texte source : anglais
Convert external GTM signals (LinkedIn posts, conference programme pages, industry pages) into engineering-first ACE artifacts, then derive wiki and GTM updates with explicit evidence boundaries.
Langue du texte source : anglais
Guardrails for multi-repo sync and branch cleanup when workspace-hub or another shared repo has active writer sessions, worktree-backed branches, or unrelated-history branches.
Langue du texte source : anglais
Safely launch overnight multi-terminal workspace-hub planning packs from isolated worktrees when the main checkout is dirty or prompts share planning/index files.
Langue du texte source : anglais
Recover overnight Claude worktree batches that appear to succeed but produce no artifacts; harden rerun prompts and launch commands.
Langue du texte source : anglais
Handle overnight planning-only lanes where plan revision/editing works but real cross-provider review dispatch is permission-blocked.
Langue du texte source : anglais
Build overnight parallel batches that close stale-open GitHub issues by proving landed work already satisfies the issue, instead of wasting implementation lanes on redoing completed work.
Langue du texte source : anglais
Run a high-leverage overnight batch by clearing stale-open approved issues first, converting shared blockers into tracked issues, and reserving only one lane for true implementation.
Langue du texte source : anglais
Use overnight Claude lanes to clear stale-open GitHub issues by verification-first closure, and convert blocked PR-repair attempts into dedicated blocker issues instead of speculative edits.
Langue du texte source : anglais
Verify overnight multi-worktree Claude batches when auto-sync, duplicate-lane convergence, and sandbox-blocked review create misleading local state or review provenance.
Langue du texte source : anglais
When repeated adversarial plan reviews keep returning MAJOR findings about validator mechanics, evidence bookkeeping, or governance traceability rather than the core product or mission decision, stop tightening the monolithic plan and split it into a…
Langue du texte source : anglais
Plan the first repo-mission canonicalization packet for the workspace ecosystem by reusing the existing control-plane issue, locking Wave-1 scope, and making review criteria deterministic.
Langue du texte source : anglais
Recover multi-repo sync failures caused by deleted upstream branches, stale git index locks, and local branches with unrelated history to the remote default branch.
Langue du texte source : anglais
Handle repository_sync cleanup when workspace-hub root is being mutated by concurrent Claude/Codex/Gemini sessions.
Langue du texte source : anglais
Catch up workspace-hub root changes that continue to appear during repo sync because live review/agent processes keep writing files after commits
Langue du texte source : anglais
Fix provider-session ecosystem audit failures caused by source-checkout imports and over-aggressive symbolic-path classification.
Langue du texte source : anglais
Actionable review routing policy — which agent reviews which agent's work, default three-agent adversarial review
Langue du texte source : anglais
Systematic audit of whether agents are following established workflows — cross-review, plan approval, TDD compliance, and document intelligence status.
Langue du texte source : anglais