donaldfilimon/abi / .agents/skills/complete-base
complete-base
VerifiedBuild the abi CLI and drive the base completion path — `abi complete "<input>"` with no flags — routing to the local model, running the constitution audit, and optionally recording the completion in WDBX. Use to smoke-test the core local-completion path after touching crates/abi-ai or the model catalog. Fully local: no --live (remote) and no --learn (SEA).
complete-base — drive abi's base local completion
Driver: .agents/skills/complete-base/complete.sh (paths relative to repo root).
Builds the CLI and drives abi complete on the base (local, non-learning) path.
Evidence is the RESULT: line. Fully local, no network.
Run (agent path)
.agents/skills/complete-base/complete.sh # default prompt, default model
.agents/skills/complete-base/complete.sh "summarize backends" fable-5 # custom prompt + model alias
complete "<prompt>"(orcomplete --model <id> "<prompt>") → assertsmodel=,audit_passed=true,wdbx kv_entries=, and apersisted=line (truewhen a durable store path is available, else honestfalse).- Model aliases are canonicalized (
fable-5→claude-fable-5); an unrecognized id passes through with a one-line stderr warning.
Prints RESULT: PASS (exit 0) or a FAIL count.
Gotchas
- ⚠️ Base path is fully local. No
--livemeans no remote provider is contacted; the response comes from the local model.--live(anthropic provider) and on-deviceapple-fm(requires--confirm) are out of scope here. --learnroutes through the SEA self-learning loop — that path is covered by thesea-learn-loopskill, not this one.- When a durable WDBX path is configured,
completemay append to that store. Without one, the CLI reportspersisted=falseandwdbx_status=no persistent WDBX path configured— both are success cases for this smoke. - For routing/catalog source, see
crates/abi-ai; SEA path issea-learn-loop.
Troubleshooting
| Symptom | Fix |
|---|---|
build FAIL | Use ./tools/cargo.sh build -p abi-cli, then ./tools/check.sh. |
audit_passed=true missing | Constitution/audit regression — check crates/abi-ai. |
unexpected model= | Alias/catalog drift — check crates/abi-ai models. |
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| rea-analysis-optimizationmorluto/reaOptimize REA providers and shared analysis workflows for agent context, latency, CPU, and memory while preserving correctness and Evidence. Use for analysis bottlenecks and cache or query design; CI/test-suite optimization belongs to rea-ci-tests-audit. | Stars: 468k | Updated | Claude CodeCodex | Verified | Install |
| rea-ci-tests-auditmorluto/reaAudit REA CI and test suites for correctness, fixture drift, false passes, and measured performance; use for suite or workflow investigations and efficiency changes, rather than ordinary feature testing or a single test failure. | Stars: 468k | Updated | Claude CodeCodex | Verified | Install |
| rea-tool-designmorluto/reaAudit, investigate, design, or change REA investigation tools, CLI/MCP contracts, provider capabilities, and Evidence semantics. | Stars: 468k | Updated | Claude CodeCodex | Verified | Install |
| ponytail-auditDietrichGebert/ponytailQuality audit of the whole repo: bugs, security, real load, missing tests, speed, and what to delete. Most important first. | Stars: 194k | Updated | Claude CodeCodex | Verified | Install |