skills/bitterblossom-dogfood/SKILL.md
Dogfood Bitterblossom by using `bb` itself to work through the Bitterblossom backlog, especially backlog.d delivery, submission storms, verdict gates, Fly Sprite execution, and operator UX notes. Use when the user asks to "dogfood Bitterblossom", "work through the Bitterblossom backlog with bb", "use bb on itself", "capture Bitterblossom friction", "run the bb backlog loop", or "test the event plane as its primary user".
npx skillsauth add misty-step/bitterblossom bitterblossom-dogfoodInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
Use Bitterblossom as the operating surface for Bitterblossom work. You are the primary user. Capture delight, friction, bugs, and missing affordances while you work, then fold the useful observations into backlog or docs.
Also load ../bitterblossom/SKILL.md for the base bb command contract.
Use references/session-notes-template.md when starting or updating a dogfood
notes artifact.
Work from /Users/phaedrus/Development/bitterblossom unless the user says
otherwise.
Run:
git status --short --branch --untracked-files=all
flyctl orgs list
sprite org list
sprite use -o misty-step lane-1
sprite org list
sprite exec -- whoami
./target/debug/bb --config plane check
./target/debug/bb --config plane status --json
./target/debug/bb --config plane task list --json
./target/debug/bb --config plane runs list --json
./target/debug/bb --config plane dlq list --json
Hard requirements:
misty-step before any remote lane or bb dispatch.
sprite org list can show another selected org; fix with
sprite use -o misty-step lane-1 and verify with sprite exec -- whoami.backlog.d/ and choose the highest leverage ready item unless
the user named one.docs/plans/ using the
template. Notes are part of the deliverable, not a side channel../scripts/verify.sh
bb:./target/debug/bb --config plane submit open \
--change "<change-key>" \
--rev "<git-sha>" \
--context "<short dogfood context>" \
--json
Then run required members with the returned submission id. Use GH_TOKEN
for the whole storm unless you have checked the task specs and know a member
does not need it; even command-backed verifier tasks may shell out to GitHub:
GH_TOKEN=$(gh auth token) ./target/debug/bb --config plane run verify \
--idempotency-key "storm:<submission>:verify" \
--payload '{"submission":"<submission>","repo":"misty-step/bitterblossom","rev":"<git-sha>","change":"<change-key>"}' \
--json
Repeat for correctness, security, simplification, and product only
when those tasks are unparked and the plane is healthy.
Evaluate:
./target/debug/bb --config plane gate --submission <submission> --json
If a required member is parked, blocked, or unavailable, record that as dogfood evidence and use the local gate plus available members. Do not hide the gap.
For every dogfood run, capture:
bb binary and plane path;Prefer concrete phrasing:
Friction: what slowed or confused you.Bug: wrong behavior or misleading output.Delight: something that made the workflow better.Lean in: a positive pattern to preserve or expand.Mitigate: a concrete fix or backlog reference.End with:
git status --short --branch --untracked-files=all
git rev-list --left-right --count master...origin/master
./target/debug/bb --config plane task list --json
./target/debug/bb --config plane dlq list --json
Report final verification, dogfood findings, residual parked/DLQ state, and the next backlog item.
tools
Operate Bitterblossom's `bb` event-plane CLI for agent workloads. Use when Codex needs to inspect or run `bb`, configure `plane.toml`, `agents/`, or `tasks/`, dispatch or audit tasks, handle runs, dead letters, recovery, parked tasks, submissions, gates, review-factory workflows, or help another repo consume Bitterblossom. Trigger phrases: "Bitterblossom", "bb", "event plane", "agent workload", "run a task", "inspect runs", "DLQ", "parked task", "submission loop", "review factory".
testing
Create, edit, improve, or audit AgentSkills. Use when creating a new skill from scratch or when asked to improve, review, audit, tidy up, or clean up an existing skill or SKILL.md file. Also use when editing or restructuring a skill directory (moving files to references/ or scripts/, removing stale content, validating against the AgentSkills spec). Triggers on phrases like "create a skill", "author a skill", "tidy up a skill", "improve this skill", "review the skill", "clean up the skill", "audit the skill".
testing
Host security hardening and risk-tolerance configuration for OpenClaw deployments. Use when a user asks for security audits, firewall/SSH/update hardening, risk posture, exposure review, OpenClaw cron scheduling for periodic checks, or version status checks on a machine running OpenClaw (laptop, workstation, Pi, VPS).
testing
Create, edit, improve, or audit AgentSkills. Use when creating a new skill from scratch or when asked to improve, review, audit, tidy up, or clean up an existing skill or SKILL.md file. Also use when editing or restructuring a skill directory (moving files to references/ or scripts/, removing stale content, validating against the AgentSkills spec). Triggers on phrases like "create a skill", "author a skill", "tidy up a skill", "improve this skill", "review the skill", "clean up the skill", "audit the skill".