SkillVaultskills Browse all 500 skills

Writing · Version 1.2.0 · Reviewed 2026-08-02

Documentation Architect

Make the reader act on task-based structure and progressive disclosure with evidence, explicit trade-offs, and a verification plan.

4 method steps 6 documented failure modes 5 diagnostic checks 7 quality gates

Structures documentation around user tasks and reading paths rather than around product structure.

₹99 one-time

Get this skill archive

What this skill helps you do

  • Task-based structure
  • Progressive disclosure
  • Navigation design

How Documentation Architect works

You provide

Schema, query plans, and the real access pattern

It inspects

Plan accuracy and lock behavior for task-based structure

It decides

A progressive disclosure change weighed against write cost

You verify

Re-measured plan with buffer reads and timing compared

What it checks first

Documentation Architect structures documentation around user tasks and reading paths rather than around product structure. Use it when the work involves Task-based structure, Progressive disclosure, Navigation design.

  1. The actual query plan with real row counts, not the estimated plan or the query text alone.
  2. Whether the workload is read-heavy, write-heavy, or mixed, since the correct design differs sharply.
  3. Transaction boundaries and duration, because long transactions block vacuum and hold locks.
  4. Index coverage relative to both the filter and the sort, since satisfying one but not the other still costs a sort.
  5. Connection pool behavior, as pool exhaustion presents as database slowness while the database is idle.

Failure modes it recognizes

  • An index that serves the predicate but not the ordering, forcing a full sort for a small LIMIT.
  • A long-running transaction preventing vacuum and causing gradual bloat and plan degradation.
  • Implicit type casting on a join or filter column silently disabling index use.
  • Connection pool exhaustion from long-held connections, appearing as a database problem.
  • A write-heavy table with excessive indexes where insert cost dominates the workload.
  • Statistics stale after a bulk load, so the planner chooses a plan for a table size that no longer exists.

Answers it will reject

  • Adding an index per slow query until write amplification becomes the new bottleneck.
  • Tuning configuration parameters before examining the plan for the dominant query.
  • Interpreting `EXPLAIN` without `ANALYZE`, which reports estimates and proves nothing.
  • Increasing pool size to fix latency caused by lock contention, which adds waiters rather than capacity.

Decision rules it applies

  • Optimize the query that dominates total time, not the one that feels slowest in isolation.
  • Order composite index columns by equality first, then range or sort last.
  • Keep transactions short and never hold one open across an external call.
  • Create and drop indexes concurrently on live tables, accepting the longer build for the absent lock.

Evidence it asks for

  • `EXPLAIN (ANALYZE, BUFFERS)` to compare estimated with actual rows and attribute I/O.
  • Rank queries by cumulative execution time rather than by single-execution latency.
  • Monitor the oldest open transaction and lock wait counts as standing metrics.

The method inside

  1. Identify the reader decision before drafting
  2. Lead with the conclusion and strongest evidence
  3. Remove unsupported claims and background that does not change action
  4. Check traceability, ambiguity, and the explicit ask

Deliverables

  • Task-based structure revised draft
  • Progressive disclosure source and logic check
  • Navigation design approval-ready version

Evidence requirements

  • Source analysis, facts, decisions, and approved claims
  • Named audience, decision, and desired action
  • Format, length, tone, and review constraints

Quality gates

  • Every material claim traces to supplied evidence or is labeled as a hypothesis.
  • The response follows the declared deliverable contract.
  • No execution, access, measurement, or verification is invented.
  • Secrets and personal data are redacted rather than repeated.
  • The user receives a concrete independent verification step.
  • The relevant failure modes in this domain were considered rather than only the reported symptom.
  • No listed anti-pattern was recommended as a solution.

Example task

Input

Our docs mirror our product structure and users still cannot find how to do common tasks.

Expected output

Mirroring product structure optimizes for the writer, which is why the search failures cluster on tasks. Restructure around the jobs users arrive with, and let reference material stay organized by product since that is how it is looked up...

Boundaries and compatibility

Ideal for

  • Task-based structure: produce a decision or artifact grounded in supplied evidence.
  • Progressive disclosure: produce a decision or artifact grounded in supplied evidence.
  • Navigation design: produce a decision or artifact grounded in supplied evidence.

Out of scope

  • Inventing facts, quotations, or approvals
  • Hiding uncertainty or material bad news

Agent compatibility

  • GitHub Copilot custom agents
  • Claude Agent Skills / SKILL.md
  • Any instruction-following chat model

Tool policy: Advisory by default. No tools are assumed. If the host provides tools, use read-only evidence gathering unless the user explicitly approves a scoped write or execution action.