Borrowing it
Nothing to install: this file belongs to existential-birds/amelia. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/existential-birds/amelia/main/.claude/skills/doc-research-improvements/SKILL.mdgit clone --depth 1 https://github.com/existential-birds/ameliaWrote 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/existential-birds/amelia/doc-research-improvements)<a href="https://agentmods.dev/skills/existential-birds/amelia/doc-research-improvements"><img src="https://agentmods.dev/badge/skills/existential-birds/amelia/doc-research-improvements/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/existential-birds/amelia/doc-research-improvements"><img src="https://agentmods.dev/badge/skills/existential-birds/amelia/doc-research-improvements.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00046 | $0.00789 |
| Opus 5.5 | $0.00018 | $0.00316 |
| Sonnet 5.5 | $0.00009 | $0.00158 |
| Haiku 4.5 | $0.00005 | $0.00079 |
Grade A, and why
doc-research-improvements 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 1mo 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 — 88 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Doc Research and Improvement (GPT-5.2)
Use this skill to analyze a single doc (architecture or idea), research its referenced concepts, and propose improvements with external sources and implementation candidates.
Input Parameters
| Parameter | Description | Required |
|---|---|---|
doc_path |
Path to the doc to analyze. | Required (unless doc_text) |
doc_text |
Raw doc content if not reading from file. | Optional |
focus_areas |
Comma list: architecture, data-model, orchestration, security, observability, testing, UX, scaling, cost. | Optional |
depth |
quick (top 3 items) or standard (top 5-8 items). |
Optional |
constraints |
Explicit constraints to respect (ex: local-first, SQLite, no background jobs). | Optional |
Repository Context (Align To)
These are core assumptions for the project (see the documentation at https://existentialbirds.com/projects/amelia):
- Amelia is a local-first, agentic coding orchestrator with LangGraph, FastAPI, and SQLite.
- Primary workflow: Architect -> Developer -> Reviewer with human approval gates.
- Design principles: structured handoffs, verify before done, environment as truth.
- Drivers and trackers are pluggable abstractions.
- Ideas are exploratory; suggest improvements without assuming commitment.
Use these as guardrails when proposing changes.
Required Workflow
-
Ingest and summarize the doc
- Identify goals, scope, non-goals, and assumptions.
- Note dependencies on current architecture or roadmap phases.
-
Extract concepts, frameworks, and techniques
- List all explicit or implied frameworks (ex: LangGraph, RAG, SOX/ICFR, BDD).
- Classify each as architecture, process, data, evaluation, or UI.
-
Research and validate
- Use authoritative sources: specs, official docs, standards, reputable research.
- Capture at least 1 source per key concept. If none, label as hypothesis.
- Summarize evidence in 1-2 lines with citations.
-
Propose improvements
- Prioritize items by impact and feasibility.
- Provide rationale tied to evidence and Amelia constraints.
- Include tradeoffs and risks.
- Call out where changes touch existing modules (ex:
amelia/core/,amelia/server/).
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.
- 1mo ago First seen · 88 lines · 46 tokens per session scan A 18114856cbc4
doc-research-improvements is a skill published in the GitHub repository existential-birds/amelia (21 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 46 tokens to every session and 789 once invoked, about $0.0002 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
find-simplifications
Use for a periodic repo-wide sweep of qwen-code for accumulated excess surface — dead components and files, orphaned locale keys, exports nothing consumes, added-then-removed scaffolding — filing candidates on a tracking issue and landing only what a maintainer has said yes to. Repo-wide and evidence-first; every…
swarm-pr-review
Run a graph-guided, tool-augmented PR review using context packing, parallel exploration, mandatory repository-agnostic risk-family coverage with dispatch scaled to diff size and risk, independent reviewer validation, critic challenge, and metrics writeback. Use for deep pull request review with low false-positive…
code-review
You are a senior code reviewer. You receive diffs via stdin.
include-test-files-that-assert-on-behavior-being-changed-in-decl
When delegating a task affected by this skill, include.
agent-debug-ci
Investigate failed scheduled or nightly GitHub Actions runs on the default branch, determine whether the failure is reproducible and repository-owned, implement the smallest evidence-backed fix, validate it, and open a pull request. Use when a failed nightly CI event starts an agent, or when the standard CI or…
audit-ci
Run and analyze Elements cold CI performance profiles and propose evidence-backed build, test, lint, and dependency-graph improvements. Use whenever asked to profile or benchmark pnpm run ci, rerun ci:profile, create a CI performance audit, compare CI timings, find bottlenecks or the completion path, investigate a CI…