Persona overlay for Professor Ada Turing, Systems Administrator of UTETY, Department of Systemic Continuity and Computational Stewardship. Loaded at boot step 7 when willow-2.0-active-persona resolves to "ada" — including the per-project default binding for the Almanac repos (almanac-data, almanac-data-dotgithub). Changes voice only — does not alter fleet identity, MCP appid, Grove sender, SOIL namespace, or active-agent.
EnglishCold instance context recovery — five-step continuity pass with runtime-specific index adapters. Use when picking up work across sessions without full boot.
EnglishApplied Reality Engineering — The Rober Rules. Diagnostic counterpart to Murphy's Law. Auto-invokes when work drifts, stalls, or spirals.
EnglishCheck whether the current session is approaching context limits. Routes to compact or handoff.
EnglishScan and wrap untrusted external content before ingestion — web, jeles, corpus, sub-agent outputs.
EnglishLive fleet health view — all agents, Postgres, Ollama, open forks, pending tasks, policy rules.
EnglishRun the complete fleet hygiene / audit sweep in one command. Use for repo litter, hook wiring, hardening scans, Kart sandbox audit closure, MCP inventory, SAFE path checks, kart-script retention, or filesystem groom — instead of hunting for repofleetsweep, hookwiringaudit, fleethardeningscan, etc.
EnglishRun KB ship-shape gates before merge or release in one command. Use for kbpreflight, embedding completeness, bitemporal audit, retrieval gold, or dry-run repairs — instead of hunting for kbpreflight.py, pgcompletenessgate.py, kbrepair.py, etc.
EnglishRun the fleet nightly metabolism (Norn pass) and optional sibling passes in one command. Use for signal promote, intake promote, sleep consolidation, session quality, or gap detection — instead of hunting for runnorn.py, sleepconsolidation.py, promotecorrections.py, etc.
EnglishRun the complete fleet session memory + benchmark pipeline in one command. Use when backfilling sessions, filling the memory tracker, running Nest benchmarks, Sonnet 5 cohort comparison, token efficiency, or Willow SLI retrieval gold — instead of hunting for sessionindexer, parsebenchmarksessions, foldproutcomes, etc.
EnglishRun weekly SLI and trust witnesses in one command. Use for WCE continuity eval, W8 census, retrieval gold, LoCoMo pilot, or CI smoke — instead of hunting for wcewitness.py, w8censuswitness.py, retrievalgoldcheck.py, etc.
EnglishGrove is the fleet chokepoint. Nothing runs without it. How to gate scripts and agents on Grove health using core/grovegate.py.
EnglishCanonical pattern for the Grove LISTEN/NOTIFY monitor used at session boot. Referenced by /startup step 5.
EnglishFleet-wide proposals on fleet — ACK/NACK quorum protocol, thresholds, and SOIL scratchpad for cross-agent votes.
EnglishPersona boot overlay for Hanuman. Loaded at boot step 7 when willow-2.0-active-persona is set to "hanuman". Changes voice and boot posture only; it does not alter fleet identity, MCP appid, Grove sender, SOIL namespace, or active-agent.
EnglishPersona boot overlay for Jeles. Loaded at boot step 7 when willow-2.0-active-persona is set to "jeles". Changes voice and boot posture only; it does not alter fleet identity, MCP appid, Grove sender, SOIL namespace, or active-agent.
EnglishPersona boot overlay for Loki. Loaded at boot step 7 when willow-2.0-active-persona is set to "loki". Changes voice and boot posture only; it does not alter fleet identity, MCP appid, Grove sender, SOIL namespace, or active-agent.
EnglishFleet orientation — MCP before grep/Bash, wired servers from manifest, operator voice from sessions not GitHub.
EnglishPersona overlay for Professor Archimedes Oakenscroll, Department of Numerical Ethics & Accidental Cosmology, University of Technical Entropy, Thank You (UTETY). Loaded at boot step 7 when willow-2.0-active-persona is set to "oakenscroll". Changes voice only — does not alter fleet identity, MCP appid, Grove sender, SOIL namespace, or active-agent.
EnglishMode A phone bridge — Discord app on phone ↔ OpenClaw gateway on desktop ↔ Grove fleet. Alerts out, grove: commands in.
EnglishFive-layer Willow memory model — flat-file boot, intake, KB, SOIL, handoff — with write rules and promotion paths.
EnglishIncludes Cold Recovery, Complexity Guard, Context Sentinel, and other workflows.
Supported by the Atlas install prompt. Skill-specific requirements vary.
Pack stats
What’s included
Ada Boot
Persona overlay for Professor Ada Turing, Systems Administrator of UTETY, Department of Systemic Continuity and Computational Stewardship. Loaded at boot step 7 when willow-2.0-active-persona resolves to "ada" — including the per-project default binding for the Almanac repos (almanac-data, almanac-data-dotgithub). Changes voice only — does not alter fleet identity, MCP appid, Grove sender, SOIL namespace, or active-agent.
Boot
Load project context efficiently (docs + structure, not all source code)
Cold Recovery
Cold instance context recovery — five-step continuity pass with runtime-specific index adapters. Use when picking up work across sessions without full boot.
Complexity Guard
Applied Reality Engineering — The Rober Rules. Diagnostic counterpart to Murphy's Law. Auto-invokes when work drifts, stalls, or spirals.
Context Sentinel
Check whether the current session is approaching context limits. Routes to compact or handoff.
External Guard
Scan and wrap untrusted external content before ingestion — web, jeles, corpus, sub-agent outputs.
Fleet Dashboard
Live fleet health view — all agents, Postgres, Ollama, open forks, pending tasks, policy rules.
Fleet Hygiene
Run the complete fleet hygiene / audit sweep in one command. Use for repo litter, hook wiring, hardening scans, Kart sandbox audit closure, MCP inventory, SAFE path checks, kart-script retention, or filesystem groom — instead of hunting for repofleetsweep, hookwiringaudit, fleethardeningscan, etc.
Fleet Kb Ship
Run KB ship-shape gates before merge or release in one command. Use for kbpreflight, embedding completeness, bitemporal audit, retrieval gold, or dry-run repairs — instead of hunting for kbpreflight.py, pgcompletenessgate.py, kbrepair.py, etc.
Fleet Metabolic
Run the fleet nightly metabolism (Norn pass) and optional sibling passes in one command. Use for signal promote, intake promote, sleep consolidation, session quality, or gap detection — instead of hunting for runnorn.py, sleepconsolidation.py, promotecorrections.py, etc.
Fleet Session Sweep
Run the complete fleet session memory + benchmark pipeline in one command. Use when backfilling sessions, filling the memory tracker, running Nest benchmarks, Sonnet 5 cohort comparison, token efficiency, or Willow SLI retrieval gold — instead of hunting for sessionindexer, parsebenchmarksessions, foldproutcomes, etc.
Fleet Witness
Run weekly SLI and trust witnesses in one command. Use for WCE continuity eval, W8 census, retrieval gold, LoCoMo pilot, or CI smoke — instead of hunting for wcewitness.py, w8censuswitness.py, retrievalgoldcheck.py, etc.
Grove Gate
Grove is the fleet chokepoint. Nothing runs without it. How to gate scripts and agents on Grove health using core/grovegate.py.
Grove Persistent Monitor
Canonical pattern for the Grove LISTEN/NOTIFY monitor used at session boot. Referenced by /startup step 5.
Grove Quorum
Fleet-wide proposals on fleet — ACK/NACK quorum protocol, thresholds, and SOIL scratchpad for cross-agent votes.
Hanuman Boot
Persona boot overlay for Hanuman. Loaded at boot step 7 when willow-2.0-active-persona is set to "hanuman". Changes voice and boot posture only; it does not alter fleet identity, MCP appid, Grove sender, SOIL namespace, or active-agent.
Jeles Boot
Persona boot overlay for Jeles. Loaded at boot step 7 when willow-2.0-active-persona is set to "jeles". Changes voice and boot posture only; it does not alter fleet identity, MCP appid, Grove sender, SOIL namespace, or active-agent.
Kart
Kart execution plane — queue shell work via agenttasksubmit instead of agent Bash.
Loki Boot
Persona boot overlay for Loki. Loaded at boot step 7 when willow-2.0-active-persona is set to "loki". Changes voice and boot posture only; it does not alter fleet identity, MCP appid, Grove sender, SOIL namespace, or active-agent.
MCP First
Fleet orientation — MCP before grep/Bash, wired servers from manifest, operator voice from sessions not GitHub.
Oakenscroll Boot
Persona overlay for Professor Archimedes Oakenscroll, Department of Numerical Ethics & Accidental Cosmology, University of Technical Entropy, Thank You (UTETY). Loaded at boot step 7 when willow-2.0-active-persona is set to "oakenscroll". Changes voice only — does not alter fleet identity, MCP appid, Grove sender, SOIL namespace, or active-agent.
OpenClaw Discord
Mode A phone bridge — Discord app on phone ↔ OpenClaw gateway on desktop ↔ Grove fleet. Alerts out, grove: commands in.
Persistent Memory Stack
Five-layer Willow memory model — flat-file boot, intake, KB, SOIL, handoff — with write rules and promotion paths.
Power
Fylgja-powers — registry + one power body (low-token router); optional id argument
Showing 24 of 31 skills. Use the list’s page controls above to explore the rest.
Quick start
- Choose your skills. Select individual skills above, or choose the entire pack.
- Copy the install prompt. Use Copy install prompt above the list.
- Send it to your agent. Paste into your coding agent’s chat. Your agent reviews the source and guides the setup.
Try it with your agent
After installation, start with a request like:
Use the Ada Boot skill to help with my task.
Ask me for the context you need before getting started.Requirements & license
- A coding agent that can access your project files and install skills.
- Your agent checks each skill’s instructions, dependencies, and permissions during setup.
- Reported license for the skills shown: Apache-2.0. The author’s terms apply.