BB workflow-memory-guardian
MANDATORY unified protocol for EVERY human user message in EVERY session at every task level: 5-phase execution discipline plus persistent cross-session memory. Workflow: classify input, clarify via 4-6 questions, plan via todo, implement, report — zero exceptions: greetings, thanks, small talk, quick questions, code, docs/PPT/Excel/PDF, charts, data analysis, web dev, follow-ups, edits. Memory: read memory files (SESSION-STATE, MEMORY) at EVERY session start BEFORE responding; checkpoint after every phase/task/decision; handoff archive at every session end incl. abrupt exits; NEVER claim 'I don't remember' without reading memory files first — session summaries are lossy, files are the source of truth. Triggers on 'lanjut', 'continue', 'kemarin', 'masih ingat?'. Pressure ('langsung kerjakan', 'jangan tanya', 'quick', 'simpel aja') compresses format, never cancels a phase. NOT for machine-generated non-user content: logs, cron, CI/CD, webhooks, alerts, auto-replies, system metadata. WAJIB di segala session.
MANDATORY unified protocol for EVERY human user message in EVERY session at every task level: 5-phase execution discipline plus persistent cross-session memory.
As a process B 68/100 · Nearly there — weak spots: result and completion, inputs and preconditions, running it twice
How to improve
- Say in the description WHEN to use the skill ("use when…", example requests): that is the agent's main cue.
- The SKILL.md body is over 5,000 tokens: move reference detail into references/ and load it when needed.
- Your own cases (evals/evals.json, 4–6 real requests with expected answers): the full check would then run those instead of a model-drafted suite.
- A spec.yaml with trigger phrases and assertions — a behaviour contract for CI; `skilltest init` writes a template.
Guard findings · 0
✓ No critical or high findings
Files scanned: 11. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
description-no-whendescription does not say WHEN to use the skill (no "use when") - warning
body-longSKILL.md body ≈ 5666 tokens (recommended < 5000); move details to references/
Process rating: all ten parameters 68/100
- 0Result and completion. Does not say what the result is
- 0Inputs and preconditions. Does not say what the process needs to start
- 0Progress reporting. Says nothing while it works
- 30Running it twice. 13 mutating operations with no state check
- 70Execution cost. Instruction body is 5666 tokens
- 100Tools and files. No external tools needed
- 100Steps. 74 steps
- 100When it triggers. States when to use and when not to
- 100Failures and branches. 1 branches, has a failure section
- 100Consistency. Name and required fields are in place
- medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
Everything here is measured from the skill text rather than judged by a model, so the numbers are checkable. A parameter weighs more when it is a more common reason for the process to stall.
Quality signals
- +5Description has no quoted example phrases that should trigger the skill
- +3Description length 1021: 120–800 characters recommended
- +3Output format is not stated: the model decides each time
- -5TODO / placeholder text left in the skill
- -4Absolute local paths (C:\Users, /home/…): not portable
- +2Single-language instructions
- +4Description says when NOT to use the skill
- +4Structure: 20 headings
- +3Step-by-step instructions: 74 items
- +4Has examples (9 code blocks)
- +4Reference files are cited in the instructions (9 of 9)
- +1License stated
Quality base 70; lint remarks subtract, signals add up to 100. Result: 59.