Agent contracts
Skill ishwarjha/lumen-product-management/skills/agent-contracts
Reference of all context slots, required vs optional declarations, and Evidence Quality standard.From its SKILL.md
npx -y skills add ishwarjha/lumen-product-management --skill agent-contractsAssembled from the repository path, not quoted from the project. Check it against their README if it does not work.
2 things to look at
- no licenseNo license file was found in the repository. Code published without one is not open source by default, so using it at work is a question for whoever answers licensing questions where you are.
- 15 stars15 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.
SKILL.md
1.8 KB, 341 tokens by cl100k_base, as published. Nobody here has run it
This skill documents the context slots agents read and write, the Evidence Quality standard, and the protocol for Required vs Optional slots.
Key v2.2 additions (ensure these appear in your machine-readable slot table):
business_model_type(EventIQ confirms in W1 Step 1)cohort_definition_method(EventIQ — how cohorts are defined)evidence_quality(per-agent evidence rating)outcome_tracking_id(DecideWell)metric_formula_map,okr_conflict_flags(NorthStar)network_effect_isolation_required(HypothesisLab)
Evidence Quality Standard (copy from Playbook §4): sample size, recency, source, completeness; overall = lowest rating across criteria.
Required vs Optional protocol:
- Required: agent must block and state missing slots.
- Optional: agent proceeds but states how missing slot would improve quality.
Canonical slot table (51 slots): schemas/context-slots.md. Update that file when adding or renaming slots; update this skill's count to match.
v2.3 additions (6 new slots added to align schema with agent outputs):
regulatory_jurisdiction— SetupGuide → DataLayer, NarrativeEngineranked_opportunity_list— DiscoveryOS → RoadMap, NorthStarresearch_synthesis_report— DiscoveryOS → NarrativeEngine, OpsCommandcategory_definition— NarrativeEngine → LaunchPad, OpsCommandaudience_messaging_matrix— NarrativeEngine → LaunchPad, OpsCommandpower_calculation— HypothesisLab → DecideWell, Orchestrator
What ships with it
Read from the repository
Just SKILL.md. No reference files, no scripts.
Gives 0 of the 12 instructions most context ai engineering skills give in 341 tokens
Counted across 1,193 of the 1,976 authors here whose files we hold, read 2026-08-07
- Dispatch a fresh implementer subagent per taskin 48 of 1193, across 19 files
- Dispatch a final code reviewer after all tasksin 33 of 1193, across 8 files
- Provide full task text to the subagentin 30 of 1193, across 9 files
- Review spec compliance before code qualityin 27 of 1193, across 10 files
- Make the hook script executablein 26 of 1193, across 8 files
- Re-snapshot after navigation or DOM changesin 25 of 1193, across 19 files
- Read files before editing themin 22 of 1193, across 11 files
- Answer subagent questions before proceedingin 22 of 1193, across 7 files
- Mark task complete in TodoWrite after approvalin 22 of 1193, across 6 files
- Merge hook into existing settingsin 21 of 1193, across 3 files
- Ask if installation is global or projectin 20 of 1193, across 2 files
- Copy the hook script to target locationin 20 of 1193, across 2 files
Said here and by no other author read
- block and state missing required slots
- proceed and state quality impact of missing optional slots
- compute evidence quality from the lowest criterion rating
- update the canonical slot file when adding slots
- update this skill's slot count to match the table
- ensure new additions appear in the machine-readable slot table
Grouped from the skills themselves: near-identical wordings counted once, and counted by distinct author, so one author publishing three of these counts once. Length counted with cl100k_base; the agent that loads this file may tokenize it differently.