All authors
Claude Skills by mifunedev
github.com/mifunedev30 skills0 installs46 views
- Agent BrowserOpen a URL in the headless agent-browser, with a preflight health check. Verifies agent-browser is installed and Chromium launches before navigating. Errors out with a diagnostic trace if anything fails. TRIGGER when: asked to open a page, browse a URL, take a screenshot, or test a site with agent-browser.Votes: 0GitHub stars: 40
- Ci StatusCheck the CI pipeline status for the current branch after pushing changes. Reports pass/fail with failure details. Use this after every push to confirm your changes are truly done — CI must be green. TRIGGER when: after git push, after committing changes, when asked to check CI, or when verifying that work is complete.Votes: 0GitHub stars: 40
- DelegateTRIGGER when: asked to "delegate this", "run this plan", "execute the stories", or "parallelize" the work. Writing or reading a plan is not a trigger and authorizes no dispatch. Runs the stories in .agro/tasks/<slug>/prd.json as bounded workers in dependency waves. The active session verifies each result, accepts it, and records it in prd.json.Votes: 0GitHub stars: 40
- Health CheckTriage memory, swap, disk and CPU where you are running, and rank Docker reclaim levers by safety×yield. Docker triage is host-only: inside a sandbox with no Docker socket the skill states that once and emits a procedure for the orchestrator to run at the host project root, rather than failing per command. TRIGGER when: asked for a health check, "do we have enough memory/disk" (container-scope inside a sandbox), before starting a heavy stack or docker build (emits the host procedure when the ...Votes: 0GitHub stars: 40
- PrdWrite or revise a repository-grounded plan for one task at .agro/tasks/<slug>/prd.md, with user stories, binary acceptance criteria, and the section headings of the feature issue template. Apply /ste. This skill plans only. It never implements the plan. TRIGGER when: "write a plan", "plan this", "plan this feature", "create a prd", "write prd for", "requirements for", "spec out".Votes: 0GitHub stars: 40
- ReleaseRelease a validated AGRO commit by pushing it to main or master, then monitor the automatic SemVer/GHCR/GitHub Release workflow. TRIGGER when: asked to release, version, ship, cut a release, or verify release artifacts.Votes: 0GitHub stars: 40
- WorktreesManage .worktrees/ lifecycle: create worktree, list worktrees, remove worktree, clean worktrees, stale worktrees audit, isolate work, project clone. TRIGGER when: any git worktree operation, branch isolation needed, stale worktrees review, project clone under projects/ (e.g. "clone <owner>/<repo> to projects", "add <repo> to projects", "clone this repo into projects"), worktree cleanup. A leading-slash harness dir like "/worktrees" still means the repo-relative .worktrees/ — never a literal f...Votes: 0GitHub stars: 40
- ArchitectDecide what the system should become before /prd writes an implementation plan. Runs inline in the active coding-agent session, grounds every claim in current repository sources, and returns one Architecture Brief. TRIGGER when: a change alters module/system boundaries, the execution or ownership model, persistent state, a security or isolation boundary, a public API or compatibility contract, a lifecycle/state machine, provider portability, shared vocabulary, cross-skill control-plane behavi...Votes: 0GitHub stars: 40
- AuditExplicit nine-target audit dispatcher for implementation promotability, one PR, the open PR queue, harness health, context budget, skill integrity, eval quality, drift, and correlated full campaigns. TRIGGER when: audit this task; verify this implementation; is this the simplest approach; audit PR N; classify this pull request; audit open PRs; triage the PR queue; audit the harness; find harness improvements; audit context budget; audit skills; find stale or broken skills; lint evals; find Go...Votes: 0GitHub stars: 40
- BenchmarkOperator-run progress-ceiling verdict gate — decide whether ONE landed change was actually BENEFICIAL (moved or held the capability-benchmark ceiling without breaking the regression floor, and is worth its complexity), then emit a single BENEFICIAL/NOT-BENEFICIAL verdict. Composes (never forks) the existing instruments: /eval (the regression floor — probes stay green) + the capability-benchmark ceiling delta (.agro/evals/capability/RESULTS.md vs. the counterfactual). Machinery added with no b...Votes: 0GitHub stars: 40
- BuilderAuthor and refine reference skills, task-style command skills, and path-scoped rules using one repository-grounded workflow. TRIGGER when: asked to create, build, scaffold, convert, review, or update a skill, command, workflow, rule, coding standard, or contextual instruction. Skills are the canonical primitive for a reusable role, procedure, or body of judgment — there is no project-agent artifact type.Votes: 0GitHub stars: 40
- ReferencesAuthor a domain or guidance skill that Claude loads inline when relevant. In AGRO, write `.agro/skills/<name>/SKILL.md`. Codex and Pi use `.agents/skills`; Claude uses `.claude/skills`. These exposure surfaces link to the canonical pack.Votes: 0GitHub stars: 40
- CloudflaredStart or explain a Cloudflared tunnel for a sandbox app port. Cloudflared is the default public sharing method for AGRO previews; this skill replaces generic sharing guidance with a portable pointer to the installed cloudflared CLI and tmux process convention. TRIGGER when: asked to share a local app publicly, expose a sandbox port, make localhost reachable from another machine, open a preview URL, or run cloudflared.Votes: 0GitHub stars: 40
- EscalateDeliver a human-addressed escalation from an unattended session to the supervisor session and to the operator's Slack channel, so a finding that needs a person does not die in a log nobody tails or a GitHub thread that notifies no one. TRIGGER when: an unattended, detached, cron, or background session is blocked and needs an operator decision; a finding requires consent the session cannot give (restart infrastructure, spend budget, change identity, publish externally); a guard or cap refuses ...Votes: 0GitHub stars: 40
- EvalRun the context fitness-function probe suite (.agro/evals/probes/*.sh) against real state and write the .agro/evals/RESULTS.md benchmark. Each probe is a deterministic 3-state oracle (PASS/REGRESSION/SKIPPED); a green→red transition is surfaced as a REGRESSION naming the lesson it closes. Tier-B behavioral evals are out of scope. TRIGGER when: asked to run evals, check the probe suite, "run /eval", verify a lesson's probe is green, benchmark the harness, or before/after editing a rule/skill t...Votes: 0GitHub stars: 40
- GitAGRO git workflow: issues, branches, commits, PR titles/bodies, changelog discipline, worktrees, branch catch-up, stacked PRs, releases, and post-push CI checks. TRIGGER when: any chat mentions git, GitHub, branches, commits, pushes, pulls, PRs, issues, worktrees, merge conflicts, dirty workspaces, changelog entries, release branch/tag workflow, or project git conventions.Votes: 0GitHub stars: 40
- HerdrDrive the Herdr terminal workspace manager from the CLI inside the AGRO sandbox — inspect and control workspaces, tabs, panes, agents, and git worktrees over the Herdr socket API, and read or steer other running agents headlessly. TRIGGER when: asked to run a `herdr` command, list/read/send to another agent or pane, check what agents are running or whether one is idle, split/focus/close panes or tabs, open or create a worktree in Herdr, wait for a pane's output or an agent's status, check Her...Votes: 0GitHub stars: 40
- Prompt MinerRank past prompts by session outcome and mine the markers that produce the best sessions. Runs the deterministic mine-traces.mjs engine over Claude + Pi JSONL traces, scores each session by a friction + ground-truth outcome proxy, ranks the initiating prompts, then synthesizes falsifiable prompt markers STRATIFIED by session type and proposes harness identity improvements behind a propose-then-confirm gate. TRIGGER when: /prompt-miner invoked, or asked to "mine prompts", "rank prompts by outc...Votes: 0GitHub stars: 40
- SteWrite and rewrite technical prose in Simplified Technical English style: short declarative sentences, active voice, imperative procedures, one term per concept, no hedges, and explicit conditions. Never simplifies code, commands, identifiers, paths, or quoted literals. Marks missing values with a placeholder rather than inventing one. Ships a deterministic checker. TRIGGER when: asked to write, rewrite, simplify, clarify, tighten, or review documentation, a README, a runbook, a spec, release ...Votes: 0GitHub stars: 40
- T3Start, inspect, pair, or stop T3 Code in the AGRO sandbox, locally or over a private Tailscale tailnet for phone access. Use this for the headless `t3 serve` harness on port 3773, including tmux launch, preflight diagnosis, pairing URL discovery, minting a pairing URL for a second device, logs, status, and shutdown. T3 Code wraps an already-authenticated Claude Code, Codex, or OpenCode backend. TRIGGER when: user asks to run T3 Code, start `t3 serve`, reach T3 Code from a phone or another mac...Votes: 0GitHub stars: 40
- WikiDispatch three subcommands: ingest, query, or lint. Manage tracked knowledge; .agro/knowledge/ owns source pages, patterns, and raw snapshots; local scratch is excluded. Canonical schema: .agro/skills/wiki/references/schema.md. Procedures: references/{ingest,query,lint}.md. TRIGGER when: ingest a URL, path, or draft; query the wiki before planning; or lint the index or review status.Votes: 0GitHub stars: 40
- SupervisorSupervise, babysit, watch, or drive advisor sessions from outside them. Run or drive an agent in another pane, including a second-pane build, and own a long build through its Definition of Done. Handle advisor briefs, compaction decisions, escalation routes, and status questions. Require MonitorCreate with onDone for observation and waits; use MonitorList and MonitorStop for handles. Never poll or use LoopCreate. Use Herdr only for launch and guarded downward steering. Block reverse Herdr mes...Votes: 0GitHub stars: 40
- CouncilCompare independent perspectives on a bounded question and return one Council Brief. The active advisor owns verification and synthesis. TRIGGER when: /council is invoked, or the user explicitly requests a council or multiple independent perspectives on a decision. Do NOT trigger for factual lookup, audit, roadmap, or implementation requests alone. Council advice does not authorize execution or publication.Votes: 0GitHub stars: 40
- Typesafe AiBuild AI-powered software with TypeSafe: small units of AI intelligence you can use like programming primitives. Its System One models, including Jev, turn natural language and application state into typed judgments and probabilities that code can combine. Use when a feature needs programmable common sense, when brainstorming what AI could make possible in an app, or when an LLM prompt-and-parse step could become a structured decision. Applications include routing, ranking, extraction, verifi...Votes: 0GitHub stars: 40
- CandidatesWrite or revise a repository-grounded plan for one task at .agro/tasks/<slug>/prd.md, with user stories, binary acceptance criteria, and the section headings of the feature issue template. Apply /ste. This skill plans only. It never implements the plan. TRIGGER when: "write a plan", "plan this", "plan this feature", "create a prd", "write prd for", "requirements for", "spec out".Votes: 0GitHub stars: 40
- Compact HandoffGenerate exactly two ready-to-paste prompts from the current conversation, labeled COMPACT_PROMPT and COMPACT_POST_PROMPT: a `/compact` command that carries the working state forward, and a post-compaction prompt that directs the next unresolved task. Prints text only; executes neither prompt. TRIGGER when: /compact-handoff is invoked, or the operator asks for a compact prompt plus a resume prompt, a compaction carry-forward, or a handoff before compacting.Votes: 0GitHub stars: 40
- BuilderAuthor and refine reference skills, task-style command skills, and path-scoped rules using one repository-grounded workflow. TRIGGER when: asked to create, build, scaffold, convert, review, or update a skill, command, workflow, rule, coding standard, or contextual instruction. Skills are the canonical primitive for a reusable role, procedure, or body of judgment — there is no project-agent artifact type.Votes: 0GitHub stars: 40
- Ci StatusCheck the CI pipeline status for the current branch after pushing changes. Reports pass/fail with failure details. Use this after every push to confirm your changes are truly done — CI must be green. TRIGGER when: after git push, after committing changes, when asked to check CI, or when verifying that work is complete.Votes: 0GitHub stars: 40
- Remote SandboxTest AGRO on a new provider VM with one command. The driver creates a VM on exe.dev or Vercel Sandbox, uploads a check, runs the check detached in the VM, polls the check log, and destroys the VM. The main scenario is the fresh install (F1 to F4). The second scenario is the AGRO hosting matrix (R01 to R15, R02b), the cgroup probe, and the VM restart test. A provider adapter of five functions and three optional hooks adds a provider. TRIGGER when: asked to validate an AGRO release or candidate...Votes: 0GitHub stars: 40
- T3Start, inspect, pair, or stop T3 Code in the AGRO sandbox, locally or over a private Tailscale tailnet for phone access. Use this for the headless `t3 serve` harness on port 3773, including tmux launch, preflight diagnosis, pairing URL discovery, minting a pairing URL for a second device, logs, status, and shutdown. T3 Code wraps an already-authenticated Claude Code, Codex, or OpenCode backend. TRIGGER when: user asks to run T3 Code, start `t3 serve`, reach T3 Code from a phone or another mac...Votes: 0GitHub stars: 40