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 ShaishavMaisuria/research-paper-lifecycle-skills --skill reflect-and-improvegit clone --depth 1 https://github.com/ShaishavMaisuria/research-paper-lifecycle-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/shaishavmaisuria/research-paper-lifecycle-skills/reflect-and-improve)<a href="https://agentmods.dev/skills/shaishavmaisuria/research-paper-lifecycle-skills/reflect-and-improve"><img src="https://agentmods.dev/badge/skills/shaishavmaisuria/research-paper-lifecycle-skills/reflect-and-improve/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/shaishavmaisuria/research-paper-lifecycle-skills/reflect-and-improve"><img src="https://agentmods.dev/badge/skills/shaishavmaisuria/research-paper-lifecycle-skills/reflect-and-improve.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 | $0.00194 | $0.02533 |
| Opus 5 | $0.00097 | $0.01267 |
| Sonnet 5 | $0.00039 | $0.00507 |
| Haiku 4.5 | $0.00019 | $0.00253 |
Grade A, and why
reflect-and-improve 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 13d 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 — 211 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Reflect and Improve
A meta-skill that runs after another skill in this toolkit produces an
artifact. It asks one question honestly: did the change actually make the
paper better, measured against the goal — or did it just make it different?
It critiques the new artifact against (a) the goal, (b) the paper's
.paper-memory/profile.yml, (c) the rubric that fits the task, and (d) past
.paper-memory/lessons.md; iterates within a hard budget; refuses to accept a
change that lowers a measurable score; and records what it learned so the next
paper starts smarter.
This is a copilot, not a pilot. It proposes; the author decides and edits.
When to use
- Just after
polish-prose,write-rebuttal,write-abstract,preflight-check,tailor-to-venue,draft-related-work, or any skill that emits an artifact, and you want a guarded second pass — "is the new version actually better, or did I introduce a regression?" - "Reflect on / critique / self-review this rewrite before I keep it."
- "Did my edit help?" / "did this get better?" / "should I revert?"
- To capture a durable lesson ("we keep over-hedging the abstract") so the whole toolkit stops repeating the mistake on this and future papers.
When NOT to use (be honest about cost)
Reflection is an extra LLM pass plus author attention. It only pays off when there is a measurable or rubric-anchored target. Skip it (or keep it to a single quick pass) when:
- There is no goal to measure against — pure preference edits ("make it sound nicer" with no rubric) reduce to taste; one read is enough.
- The producing skill already emits a hard score that did not change (e.g. a preflight that was clean before and after). Re-running its checker IS the reflection; do that instead of a narrative critique.
- The artifact is tiny (a one-line fix). The loop's overhead exceeds its value.
Say this to the user when they ask to reflect on something unmeasurable, then offer the single-pass version.
Inputs
What ships with it
3 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.
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.
- 13d ago First seen · 211 lines · 194 tokens per session scan A a2f052c805d8
reflect-and-improve is a skill published in the GitHub repository ShaishavMaisuria/research-paper-lifecycle-skills (42 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 194 tokens to every session and 2,533 once invoked, about $0.0010 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
aaai-reproducibility
Use when strengthening an AAAI paper's reproducibility checklist (placed after references), experimental traceability, seed and hyperparameter reporting, compute and cost disclosure, dataset access and licensing, code/data ZIP readiness, and the claim-to-evidence map that Phase-1 reviewers use to judge rigor across…
aaai-submission
Use when auditing an AAAI main technical track submission for OpenReview readiness, double-blind anonymity, page limits, reproducibility checklist, supplementary material, author limits, multiple-submission policy, and AAAI AI-use policy compliance.
aaai-topic-selection
Use when deciding whether a project is a strong AAAI submission across its broad AI scope, should be reframed or routed to a dedicated track such as AI for Social Impact or AI Alignment, or should instead go to IJCAI, NeurIPS, ICML, ICLR, AISTATS, UAI, ACL, CVPR, KDD, CHI, ICRA, or another specialist venue.
acl-author-response
Use when drafting an ACL author response inside an ACL Rolling Review cycle on OpenReview, covering the response window before meta-review, reviewer discussion dynamics, score-change strategy, flagging review issues to the area chair, anonymity rules, and deciding between responding now versus revising for a later ARR…
acl-camera-ready
Use when preparing an accepted ACL main-conference or Findings paper for camera-ready, covering the extra content page, de-anonymization and acknowledgements, AI-assistance disclosure, keeping the Limitations section, ACL Anthology metadata and CC BY 4.0 publication, meta-review-driven edits, and presentation-mode…
acl-experiments
Use when designing or auditing experiments for an ACL paper, covering tuned LLM baselines, multi-dataset and multilingual evaluation, statistical significance and variance, human evaluation with agreement reporting, contamination and prompt-sensitivity controls, ablations, and error-analysis expectations in NLP…