Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add tikalk/adlc-team-skills --skill product-implementgit clone --depth 1 https://github.com/tikalk/adlc-team-skillsWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/tikalk/adlc-team-skills/product-implement)<a href="https://agentmods.dev/skills/tikalk/adlc-team-skills/product-implement"><img src="https://agentmods.dev/badge/skills/tikalk/adlc-team-skills/product-implement/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/tikalk/adlc-team-skills/product-implement"><img src="https://agentmods.dev/badge/skills/tikalk/adlc-team-skills/product-implement.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00021 | $0.03958 |
| Opus 5.5 | $0.00008 | $0.01583 |
| Sonnet 5.5 | $0.00004 | $0.00792 |
| Haiku 4.5 | $0.00002 | $0.00396 |
Grade A, and why
product-implement scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 5d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 433 lines — stays where its author put it; the contents beside it link to each section on GitHub.
product-implement
What this skill does
Transforms accepted PDRs into a comprehensive, self-contained PRD.md using a three-phase DAG:
- Plan Agent: Analyze PDRs, detect feature-areas, generate customized DAG, get user approval
- Execute Agent: Generate sections per feature-area with mandatory checkpoint after Requirements
- Summarize Agent: Aggregate sections, resolve conflicts, produce unified
PRD.md
Output:
docs/adlc/product/PRD.md— self-contained product requirements (the shared layout; legacy repo-rootPRD.mdstays read-compatible){REPO_ROOT}/.adlc/product/sections/{feature-area}/{section}.md— intermediate section files- Accepted PDRs moved to
{REPO_ROOT}/docs/adlc/memory/pdr/(the shared layout canonical memory root)
When to use
- After
/product-clarifyhas approved PDRs - After
/product-initto document existing product - PDR updates requiring PRD regeneration
When NOT to use
- No Accepted PDRs (run
/product-clarifyfirst) - Minor PRD edits (edit
PRD.mddirectly)
Pre-Flight Validation
Before starting, verify prerequisites:
- Check PDRs exist:
{REPO_ROOT}/.adlc/drafts/pdr/PDR-*.md - Check for Accepted PDRs: Count files with status "Accepted"
- If zero: STOP and output:
Cannot proceed: No Accepted PDRs found. Run /product-clarify to review and approve PDRs first. - If ≥1: Proceed
- If zero: STOP and output:
Three-Phase DAG Workflow
┌─────────────────────────────────────────────────────────┐
│ PHASE 1: PLAN (Plan Agent) │
│ Load PDRs → Detect Feature-Areas → Generate DAG → Approve│
└─────────────────────────────────────────────────────────┘
↓
┌─────────────────────────────────────────────────────────┐
│ PHASE 2: EXECUTE (Execute Agent) │
│ Overview → Problem → Goals → Metrics → Personas │
│ → [REQUIREMENTS CHECKPOINT] ← MANDATORY USER APPROVAL │
│ → NFRs → Out-of-Scope → Risks → Roadmap → PDR-Summary │
└─────────────────────────────────────────────────────────┘
↓
┌─────────────────────────────────────────────────────────┐
│ PHASE 3: SUMMARIZE (Summarize Agent) │
│ Read sections → Detect conflicts → Resolve → PRD.md │
└─────────────────────────────────────────────────────────┘
What ships with it
7 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- scripts/bash/migrate-pdr-frontmatter.sh 9.5 KB runs code
- scripts/bash/setup-product-implement.sh 2.5 KB runs code
- scripts/bash/validate-pdr.sh 1.6 KB runs code
- scripts/bash/validate-prd.sh 14 KB runs code
- scripts/powershell/setup-product-implement.ps1 1.9 KB runs code
- scripts/powershell/validate-pdr.ps1 2.2 KB runs code
- scripts/powershell/validate-prd.ps1 16 KB runs code
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 5d ago Changed 217b38c41dc8
- 25d ago Changed 6e5fd7c837dd
- 26d ago Changed · +2 lines 40dd6910bdba
- 1mo ago Changed 2de0bf1b66e2
- 1mo ago Changed · -39 tokens per session cb2ead7ba554
- 1mo ago Changed · +11 lines 84c3385922e4
- 1mo ago First seen · 420 lines · 60 tokens per session scan A 99f36e9b1c95
product-implement is a skill published in the GitHub repository tikalk/adlc-team-skills (143 stars, last pushed today), licensed MIT. It adds 21 tokens to every session and 3,958 once invoked, about $0.0001 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
building-agents
Use when building or restructuring an LLM agent — provider adapter, tool calling, structured output, RAG, agent loop, eval gate, cost routing, tracing, MCP server — model-agnostic across OpenAI/Anthropic/Gemini/OSS so a model swap is a config change. NOT vector-store SQL alone (that is postgresdb) or service…
agent-eval
Use when measuring whether an LLM or agent system actually got better and gating merges on it: golden sets, fixing an inflated LLM-as-judge, scoring RAG (faithfulness, contextual recall) or agent trajectories (tool correctness, completion), or picking an eval framework. NOT building the agent loop, tools or RAG…
decision-records
Use when a hard-to-reverse choice (database, framework, vendor, auth model) must be frozen as an immutable numbered ADR — the context that forced it, the options weighed, the decision, consequences both ways — or superseded without erasing history. NOT a meeting recap (that is meeting-notes), NOT standing project…
prompt-engineering
Use when one prompt must give the same right answer across reruns, models, and pasted-in hostile input: forcing a fixed schema, picking the few-shot set, ordering the prompt blocks, or the inline cases you run while tuning. NOT the agent loop, tools, or retrieval (that is building-agents), NOT a standing CI eval…
respect-the-oracle
Use when working against a test suite, spec, or graded harness you do not own - especially inside an automated loop scored on how many tests pass - and tempted to change the tests, weaken assertions, hardcode expected outputs, special-case inputs, or overfit the visible examples to turn things green.
refocusing
Use when a long-running agent may have lost the product outcome, when context was compacted, when work has crossed a major boundary, or when a fresh path-based trace is needed before the next consequential action. Not for fresh-session orientation, waking an idle seat, or checkpoints.