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 | $0.00023 | $0.00394 |
| Sonnet 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 9d 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.
- 9d 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 today), licensed Apache-2.0. It adds 46 tokens to every session and 789 once invoked, about $0.0002 per session on Opus 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
code-review
You are a senior code reviewer. You receive diffs via stdin.
review
Two-stage code review: spec compliance first, then code quality. Auto-triggered after implementation. Also available as /review.
devils-advocate
Challenge a plan, design, or PR by finding every flaw, risk, and wrong assumption. Use before committing to an architecture or shipping a major change.
naming-format
Use when reviewing file names, renaming files, fixing naming conventions, or auditing exports. Enforces consistent casing and suffix patterns.
security-review
Adversarial security review of a change (branch diff, PR, or working tree) before merge. Use when the user asks to "review this for security", "security review", "check for vulnerabilities", "is this safe to merge", or before merging anything that touches a trust boundary — auth/authz, input parsing…
design-system
Frontend design conventions for {{ projectname }} -- layout hierarchy, spacing, typography, anti-slop rules. Auto-activates when creating or modifying templates, CSS, or frontend components.